参考文献References

• [1] Martín Abadi 等，“TensorFlow: Large-scale machine learning on heterogeneous distributed systems”，载于 arXiv preprint arXiv:1603.04467，2016 年[1] Martín Abadi et al. “Tensorflow: Large-scale machine learning on heterogeneous distributed systems” In arXiv preprint arXiv:1603.04467, 2016
• [2] Jacob Abernethy、Chansoo Lee 与 Ambuj Tewari，“Perturbation techniques in online learning and optimization”，载于 Perturbations, Optimization, and Statistics 233，MIT Press，2016 年[2] Jacob Abernethy, Chansoo Lee and Ambuj Tewari “Perturbation techniques in online learning and optimization” In Perturbations, Optimization, and Statistics 233 MIT Press, 2016
• [3] Arash Ahmadian 等，“Back to basics: Revisiting reinforce style optimization for learning from human feedback in LLMs”，载于 arXiv preprint arXiv:2402.14740，2024 年[3] Arash Ahmadian et al. “Back to basics: Revisiting reinforce style optimization for learning from human feedback in llms” In arXiv preprint arXiv:2402.14740, 2024
• [4] Srinivas Aji 与 Robert McEliece，“The generalized distributive law”，载于 IEEE Transactions on Information Theory 46.2，IEEE，2000 年，第 325–343 页[4] Srinivas Aji and Robert McEliece “The generalized distributive law” In IEEE transactions on Information Theory 46.2 IEEE, 2000, pp. 325–343
• [5] Shun-Ichi Amari，“Natural gradient works efficiently in learning”，载于 Neural Computation 10.2，MIT Press，1998 年，第 251–276 页[5] Shun-Ichi Amari “Natural gradient works efficiently in learning” In Neural computation 10.2 MIT Press, 1998, pp. 251–276
• [6] Jimmy Ba、Jamie Kiros 与 Geoffrey Hinton，“Layer normalization”，载于 arXiv preprint arXiv:1607.06450，2016 年[6] Jimmy Ba, Jamie Kiros and Geoffrey Hinton “Layer normalization” In arXiv preprint arXiv:1607.06450, 2016
• [7] Francis Bach、Rodolphe Jenatton、Julien Mairal 与 Guillaume Obozinski，“Optimization with sparsity-inducing penalties”，载于 Foundations and Trends® in Machine Learning 4.1，Now Publishers, Inc.，2012 年，第 1—106 页[7] Francis Bach, Rodolphe Jenatton, Julien Mairal and Guillaume Obozinski “Optimization with sparsity-inducing penalties” In Foundations and Trends® in Machine Learning 4.1 Now Publishers, Inc., 2012, pp. 1–106
• [8] Keith Ball、Eric Carlen 与 Elliott Lieb，“Sharp uniform convexity and smoothness inequalities for trace norms”，载于 Inequalities: Selecta of Elliott H. Lieb，Springer，2002 年，第 171—190 页[8] Keith Ball, Eric Carlen and Elliott Lieb “Sharp uniform convexity and smoothness inequalities for trace norms” In Inequalities: Selecta of Elliott H. Lieb Springer, 2002, pp. 171–190
• [9] Walter Ball，《A short account of the history of mathematics》，Courier Corporation，1960 年[9] Walter Ball “A short account of the history of mathematics” Courier Corporation, 1960
• [10] Matej Balog、Nilesh Tripuraneni、Zoubin Ghahramani 与 Adrian Weller，“Lost relatives of the Gumbel trick”，载于 International Conference on Machine Learning，2017 年，第 371—379 页，PMLR[10] Matej Balog, Nilesh Tripuraneni, Zoubin Ghahramani and Adrian Weller “Lost relatives of the Gumbel trick” In International Conference on Machine Learning, 2017, pp. 371–379 PMLR
• [11] Ole Barndorff-Nielsen，《Information and exponential families: in statistical theory》，John Wiley & Sons，2014 年[11] Ole Barndorff-Nielsen “Information and exponential families: in statistical theory” John Wiley & Sons, 2014
• [12] Robert Baston 与 Yuji Nakatsukasa，“Stochastic diagonal estimation: probabilistic bounds and an improved algorithm”，载于 arXiv preprint arXiv:2201.10684，2022 年[12] Robert Baston and Yuji Nakatsukasa “Stochastic diagonal estimation: probabilistic bounds and an improved algorithm” In arXiv preprint arXiv:2201.10684, 2022
• [13] Leonard Baum 与 Ted Petrie，“Statistical inference for probabilistic functions of finite state Markov chains”，载于 The annals of mathematical statistics 37.6，JSTOR，1966 年，第 1554—1563 页[13] Leonard Baum and Ted Petrie “Statistical inference for probabilistic functions of finite state Markov chains” In The annals of mathematical statistics 37.6 JSTOR, 1966, pp. 1554–1563
• [14] Walter Baur 与 Volker Strassen，“The complexity of partial derivatives”，载于 Theoretical computer science 22.3，Elsevier，1983 年，第 317—330 页[14] Walter Baur and Volker Strassen “The complexity of partial derivatives” In Theoretical computer science 22.3 Elsevier, 1983, pp. 317–330
• [15] H. Bauschke Heinz 与 L. Combettes Patrick，“Convex Analysis and Monotone Operator Theory in Hilbert Spaces, 2011”，载于 CMS books in mathematics.，2017 年，第 978—1 页[15] H. Bauschke Heinz and L. Combettes Patrick “Convex Analysis and Monotone Operator Theory in Hilbert Spaces, 2011” In CMS books in mathematics., 2017, pp. 978–1
• [16] Atilim Baydin、Barak Pearlmutter、Alexey Radul 与 Jeffrey Siskind，“Automatic differentiation in machine learning: a survey”，载于 Journal of Marchine Learning Research 18，Microtome Publishing，2018 年，第 1—43 页[16] Atilim Baydin, Barak Pearlmutter, Alexey Radul and Jeffrey Siskind “Automatic differentiation in machine learning: a survey” In Journal of Marchine Learning Research 18 Microtome Publishing, 2018, pp. 1–43
• [17] Atılımüneş Baydin 等，“Gradients without backpropagation”，载于 arXiv preprint arXiv:2202.08587，2022 年[17] Atılımüneş Baydin et al. “Gradients without backpropagation” In arXiv preprint arXiv:2202.08587, 2022
• [18] Amir Beck，《First-order methods in optimization》，SIAM，2017 年[18] Amir Beck “First-order methods in optimization” SIAM, 2017
• [19] Amir Beck 与 Marc Teboulle，“Smoothing and first order methods: A unified framework”，载于 SIAM Journal on Optimization 22.2，SIAM，2012 年，第 557—580 页[19] Amir Beck and Marc Teboulle “Smoothing and first order methods: A unified framework” In SIAM Journal on Optimization 22.2 SIAM, 2012, pp. 557–580
• [20] Sue Becker 与 Yann Le，“Improving the convergence of back-propagation learning with second order methods”，载于 Proceedings of the 1988 connectionist models summer school，1988 年，第 29—37 页[20] Sue Becker and Yann Le “Improving the convergence of back-propagation learning with second order methods” In Proceedings of the 1988 connectionist models summer school, 1988, pp. 29–37
• [21] Costas Bekas、Effrosyni Kokiopoulou 与 Yousef Saad，“An estimator for the diagonal of a matrix”，载于 Applied numerical mathematics 57.11-12，Elsevier，2007 年，第 1214—1229 页[21] Costas Bekas, Effrosyni Kokiopoulou and Yousef Saad “An estimator for the diagonal of a matrix” In Applied numerical mathematics 57.11-12 Elsevier, 2007, pp. 1214–1229
• [22] James Bergstra 等，“Theano: a CPU and GPU math expression compiler”，载于 Proceedings of the Python for scientific computing conference（SciPy）4.3，德克萨斯州奥斯汀，2010 年，第 1—7 页[22] James Bergstra et al. “Theano: a CPU and GPU math expression compiler” In Proceedings of the Python for scientific computing conference (SciPy) 4.3, 2010, pp. 1–7 Austin, TX
• [23] Quentin Berthet 等，“Learning with differentiable pertubed optimizers”，载于 Advances in neural information processing systems 33，2020 年，第 9508—9519 页[23] Quentin Berthet et al. “Learning with differentiable pertubed optimizers” In Advances in neural information processing systems 33, 2020, pp. 9508–9519
• [24] Dimitri Bertsekas，“Nonlinear programming”，载于 Journal of the Operational Research Society 48.3，Taylor & Francis，1997 年，第 334—334 页[24] Dimitri Bertsekas “Nonlinear programming” In Journal of the Operational Research Society 48.3 Taylor & Francis, 1997, pp. 334–334
• [25] Guy Blelloch，“Scans as primitive parallel operations”，载于 IEEE Transactions on computers 38.11，IEEE，1989 年，第 1526—1538 页[25] Guy Blelloch “Scans as primitive parallel operations” In IEEE Transactions on computers 38.11 IEEE, 1989, pp. 1526–1538
• [26] Mathieu Blondel，“Structured prediction with projection oracles”，载于 Advances in neural information processing systems 32，2019 年[26] Mathieu Blondel “Structured prediction with projection oracles” In Advances in neural information processing systems 32, 2019
• [27] Mathieu Blondel 等，“Efficient and Modular Implicit Differentiation”，载于 arXiv preprint arXiv:2105.15183，2021 年[27] Mathieu Blondel et al. “Efficient and Modular Implicit Differentiation” In arXiv preprint arXiv:2105.15183, 2021
• [28] Mathieu Blondel、André Martins 与 Vlad Niculae，“Learning with fenchel-young losses”，载于 The Journal of Machine Learning Research 21.1，JMLRORG，2020 年，第 1314—1382 页[28] Mathieu Blondel, André Martins and Vlad Niculae “Learning with fenchel-young losses” In The Journal of Machine Learning Research 21.1 JMLRORG, 2020, pp. 1314–1382
• [29] Jérôme Bolte、Ryan Boustany、Edouard Pauwels 与 Béatrice Pesquet-Popescu，“On the complexity of nonsmooth automatic differentiation”，载于 The Eleventh International Conference on Learning Representations，2022 年[29] Jérôme Bolte, Ryan Boustany, Edouard Pauwels and Béatrice Pesquet-Popescu “On the complexity of nonsmooth automatic differentiation” In The Eleventh International Conference on Learning Representations, 2022
• [30] Jérôme Bolte 与 Edouard Pauwels，“A mathematical model for automatic differentiation in machine learning”，载于 Advances in Neural Information Processing Systems 33，2020 年，第 10809—10819 页[30] Jérôme Bolte and Edouard Pauwels “A mathematical model for automatic differentiation in machine learning” In Advances in Neural Information Processing Systems 33, 2020, pp. 10809–10819
• [31] Aleksandar Botev、Hippolyt Ritter 与 David Barber，“Practical Gauss-Newton optimisation for deep learning”，载于 International Conference on Machine Learning，2017 年，第 557—565 页[31] Aleksandar Botev, Hippolyt Ritter and David Barber “Practical Gauss-Newton optimisation for deep learning” In International Conference on Machine Learning, 2017, pp. 557–565
• [32] Nicolas Boumal，《An introduction to optimization on smooth manifolds》，Cambridge University Press，2023 年[32] Nicolas Boumal “An introduction to optimization on smooth manifolds” Cambridge University Press, 2023
• [33] Stephen Boyd 与 Lieven Vandenberghe，《Convex optimization》，Cambridge university press，2004 年[33] Stephen Boyd and Lieven Vandenberghe “Convex optimization” Cambridge university press, 2004
• [34] James Bradbury 等，“JAX: composable transformations of Python+NumPy programs”，2018 年，URL：http://github.com/google/jax[34] James Bradbury et al. “JAX: composable transformations of Python+NumPy programs”, 2018 URL: http://github.com/google/jax
• [35] Martin Braun 与 Martin Golubitsky，《Differential equations and their applications》，Springer，1983 年[35] Martin Braun and Martin Golubitsky “Differential equations and their applications” Springer, 1983
• [36] Dimo Brockhoff 等，“Mirrored sampling and sequential selection for evolution strategies”，载于 Parallel Problem Solving from Nature, PPSN XI: 11th International Conference, Kraków, Poland, September 11-15, 2010, Proceedings, Part I 11，2010 年，第 11—21 页，Springer[36] Dimo Brockhoff et al. “Mirrored sampling and sequential selection for evolution strategies” In Parallel Problem Solving from Nature, PPSN XI: 11th International Conference, Kraków, Poland, September 11-15, 2010, Proceedings, Part I 11, 2010, pp. 11–21 Springer
• [37] Charles Broyden，“The convergence of a class of double-rank minimization algorithms 1. general considerations”，载于 IMA Journal of Applied Mathematics 6.1，Oxford University Press，1970 年，第 76—90 页[37] Charles Broyden “The convergence of a class of double-rank minimization algorithms 1. general considerations” In IMA Journal of Applied Mathematics 6.1 Oxford University Press, 1970, pp. 76–90
• [38] Peter Brucker，“An $O(n)$ algorithm for quadratic knapsack problems”，载于 Operations Research Letters 3.3，Elsevier，1984 年，第 163—166 页[38] Peter Brucker “An $O(n)$ algorithm for quadratic knapsack problems” In Operations Research Letters 3.3 Elsevier, 1984, pp. 163–166
• [39] John Butcher，《Numerical methods for ordinary differential equations》，John Wiley & Sons，2016 年[39] John Butcher “Numerical methods for ordinary differential equations” John Wiley & Sons, 2016
• [40] Florian Cajori，《A history of mathematical notations》，Courier Corporation，1993 年[40] Florian Cajori “A history of mathematical notations” Courier Corporation, 1993
• [41] Jean Céa，“Conception optimale ou identification de formes, calcul rapide de la dérivée directionnelle de la fonction coût”，载于 M2AN-Modélisation mathématique et analyse numérique 20.3，1986 年，第 371—402 页[41] Jean Céa “Conception optimale ou identification de formes, calcul rapide de la dérivée directionnelle de la fonction coût” In M2AN-Modélisation mathématique et analyse numérique 20.3, 1986, pp. 371–402
• [42] Swarat Chaudhuri 与 Armando Solar-Lezama，“Smooth interpretation”，载于 ACM Sigplan Notices 45.6，ACM New York, NY, USA，2010 年，第 279—291 页[42] Swarat Chaudhuri and Armando Solar-Lezama “Smooth interpretation” In ACM Sigplan Notices 45.6 ACM New York, NY, USA, 2010, pp. 279–291
• [43] Ricky Chen、Yulia Rubanova、Jesse Bettencourt 与 David Duvenaud，“Neural ordinary differential equations”，载于 Advances in neural information processing systems 31，2018 年[43] Ricky Chen, Yulia Rubanova, Jesse Bettencourt and David Duvenaud “Neural ordinary differential equations” In Advances in neural information processing systems 31, 2018
• [44] Xi Chen、Neeraj Kayal 与 Avi Wigderson，“Partial derivatives in arithmetic complexity and beyond”，载于 Foundations and Trends® in Theoretical Computer Science 6.1–2，2011 年，第 1—138 页[44] Xi Chen, Neeraj Kayal and Avi Wigderson “Partial derivatives in arithmetic complexity and beyond” In Foundations and Trends® in Theoretical Computer Science 6.1–2, 2011, pp. 1–138
• [45] Francis Clarke、Yuri Ledyaev、Ronald Stern 与 Peter Wolenski，《Nonsmooth analysis and control theory》，Springer Science & Business Media，2008 年[45] Francis Clarke, Yuri Ledyaev, Ronald Stern and Peter Wolenski “Nonsmooth analysis and control theory” Springer Science & Business Media, 2008
• [46] Frank Clarke，“Generalized gradients and applications”，载于 Transactions of the American Mathematical Society 205，1975 年，第 247—262 页[46] Frank Clarke “Generalized gradients and applications” In Transactions of the American Mathematical Society 205, 1975, pp. 247–262
• [47] Donald Cohn，《Measure theory》，Springer，2013 年[47] Donald Cohn “Measure theory” Springer, 2013
• [48] Laurent Condat，“Fast projection onto the simplex and the $\ell_{1}$ ball”，载于 Mathematical Programming 158.1-2，Springer，2016 年，第 575—585 页[48] Laurent Condat “Fast projection onto the simplex and the $\ell_{1}$ ball” In Mathematical Programming 158.1-2 Springer, 2016, pp. 575–585
• [49] David Dalrymple，“Differentiable Programming”，2016 年，URL：https://www.edge.org/response-detail/26794[49] David Dalrymple “Differentiable Programming”, 2016 URL: https://www.edge.org/response-detail/26794
• [50] Felix Dangel、Frederik Kunstner 与 Philipp Hennig，“Backpack: Packing more into backprop”，载于 arXiv preprint arXiv:1912.10985，2019 年[50] Felix Dangel, Frederik Kunstner and Philipp Hennig “Backpack: Packing more into backprop” In arXiv preprint arXiv:1912.10985, 2019
• [51] John Danskin，“The theory of max-min, with applications”，载于 SIAM Journal on Applied Mathematics 14.4，SIAM，1966 年，第 641—664 页[51] John Danskin “The theory of max-min, with applications” In SIAM Journal on Applied Mathematics 14.4 SIAM, 1966, pp. 641–664
• [52] Jared Davis 等，“Time dependence in non-autonomous neural odes”，载于 arXiv preprint arXiv:2005.01906，2020 年[52] Jared Davis et al. “Time dependence in non-autonomous neural odes” In arXiv preprint arXiv:2005.01906, 2020
• [53] Morris DeGroot，“Uncertainty, information, and sequential experiments”，载于 The Annals of Mathematical Statistics 33.2，Institute of Mathematical Statistics，1962 年，第 404—419 页[53] Morris DeGroot “Uncertainty, information, and sequential experiments” In The Annals of Mathematical Statistics 33.2 Institute of Mathematical Statistics, 1962, pp. 404–419
• [54] Mostafa Dehghani 等，“Scaling vision transformers to 22 billion parameters”，载于 International Conference on Machine Learning，2023 年，第 7480—7512 页，PMLR[54] Mostafa Dehghani et al. “Scaling vision transformers to 22 billion parameters” In International Conference on Machine Learning, 2023, pp. 7480–7512 PMLR
• [55] Marc Deisenroth、A Faisal 与 Cheng Ong，《Mathematics for machine learning》，Cambridge University Press，2020 年[55] Marc Deisenroth, A Faisal and Cheng Ong “Mathematics for machine learning” Cambridge University Press, 2020
• [56] Jacob Devlin、Ming-Wei Chang、Kenton Lee 与 Kristina Toutanova，“BERT: Pre-training of deep bidirectional transformers for language understanding”，载于 Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies，第 1 卷（long and short papers），2019 年，第 4171—4186 页[56] Jacob Devlin, Ming-Wei Chang, Kenton Lee and Kristina Toutanova “BERT: Pre-training of deep bidirectional transformers for language understanding” In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers), 2019, pp. 4171–4186
• [57] Dmitriy Drusvyatskiy 与 Courtney Paquette，“Efficiency of minimizing compositions of convex functions and smooth maps”，载于 Mathematical Programming 178，Springer，2019 年，第 503—558 页[57] Dmitriy Drusvyatskiy and Courtney Paquette “Efficiency of minimizing compositions of convex functions and smooth maps” In Mathematical Programming 178 Springer, 2019, pp. 503–558
• [58] John Duchi、Michael Jordan、Martin Wainwright 与 Andre Wibisono，“Optimal rates for zero-order convex optimization: The power of two function evaluations”，载于 IEEE Transactions on Information Theory 61.5，IEEE，2015 年，第 2788—2806 页[58] John Duchi, Michael Jordan, Martin Wainwright and Andre Wibisono “Optimal rates for zero-order convex optimization: The power of two function evaluations” In IEEE Transactions on Information Theory 61.5 IEEE, 2015, pp. 2788–2806
• [59] John Duchi、Shai Shalev-Shwartz、Yoram Singer 与 Tushar Chandra，“Efficient projections onto the $\ell_{1}$-ball for learning in high dimensions”，载于 Proc. of ICML，2008 年[59] John Duchi, Shai Shalev-Shwartz, Yoram Singer and Tushar Chandra “Efficient projections onto the $\ell_{1}$-ball for learning in high dimensions” In Proc. of ICML, 2008
• [60] Philipp Dufter、Martin Schmitt 与 Hinrich Schütze，“Position information in transformers: An overview”，载于 Computational Linguistics 48.3，MIT Press One Broadway, 12th Floor, Cambridge, Massachusetts 02142, USA …，2022 年，第 733—763 页[60] Philipp Dufter, Martin Schmitt and Hinrich Schütze “Position information in transformers: An overview” In Computational Linguistics 48.3 MIT Press One Broadway, 12th Floor, Cambridge, Massachusetts 02142, USA …, 2022, pp. 733–763
• [61] Jason Eisner，“Inside-outside and forward-backward algorithms are just backprop (tutorial paper)”，载于 Proceedings of the Workshop on Structured Prediction for NLP，2016 年，第 1—17 页[61] Jason Eisner “Inside-outside and forward-backward algorithms are just backprop (tutorial paper)” In Proceedings of the Workshop on Structured Prediction for NLP, 2016, pp. 1–17
• [62] Mohamed Elsayed 与 A Mahmood，“HesScale: Scalable Computation of Hessian Diagonals”，载于 arXiv preprint arXiv:2210.11639，2022 年[62] Mohamed Elsayed and A Mahmood “HesScale: Scalable Computation of Hessian Diagonals” In arXiv preprint arXiv:2210.11639, 2022
• [63] Ethan Epperly、Joel Tropp 与 Robert Webber，“XTrace: Making the most of every sample in stochastic trace estimation”，载于 arXiv preprint arXiv:2301.07825，2023 年[63] Ethan Epperly, Joel Tropp and Robert Webber “XTrace: Making the most of every sample in stochastic trace estimation” In arXiv preprint arXiv:2301.07825, 2023
• [64] António Farinhas、Wilker Aziz、Vlad Niculae 与 André Martins，“Sparse communication via mixed distributions”，载于 arXiv preprint arXiv:2108.02658，2021 年[64] António Farinhas, Wilker Aziz, Vlad Niculae and André Martins “Sparse communication via mixed distributions” In arXiv preprint arXiv:2108.02658, 2021
• [65] Harley Flanders，“Differentiation under the integral sign”，载于 The American Mathematical Monthly 80.6，Taylor & Francis，1973 年，第 615—627 页[65] Harley Flanders “Differentiation under the integral sign” In The American Mathematical Monthly 80.6 Taylor & Francis, 1973, pp. 615–627
• [66] Wendell Fleming 与 Raymond Rishel，《Deterministic and stochastic optimal control》，Springer Science & Business Media，2012 年[66] Wendell Fleming and Raymond Rishel “Deterministic and stochastic optimal control” Springer Science & Business Media, 2012
• [67] Roger Fletcher，“A new approach to variable metric algorithms”，载于 The computer journal 13.3，Oxford University Press，1970 年，第 317—322 页[67] Roger Fletcher “A new approach to variable metric algorithms” In The computer journal 13.3 Oxford University Press, 1970, pp. 317–322
• [68] Jakob Foerster 等，“Dice: The infinitely differentiable monte carlo estimator”，载于 International Conference on Machine Learning，2018 年，第 1529—1538 页，PMLR[68] Jakob Foerster et al. “Dice: The infinitely differentiable monte carlo estimator” In International Conference on Machine Learning, 2018, pp. 1529–1538 PMLR
• [69] G Forney，“The viterbi algorithm”，载于 Proceedings of the IEEE 61.3，Ieee，1973 年，第 268—278 页[69] G Forney “The viterbi algorithm” In Proceedings of the IEEE 61.3 Ieee, 1973, pp. 268–278
• [70] Luca Franceschi、Michele Donini、Paolo Frasconi 与 Massimiliano Pontil，“Forward and reverse gradient-based hyperparameter optimization”，载于 International Conference on Machine Learning，2017 年，第 1165—1173 页，PMLR[70] Luca Franceschi, Michele Donini, Paolo Frasconi and Massimiliano Pontil “Forward and reverse gradient-based hyperparameter optimization” In International Conference on Machine Learning, 2017, pp. 1165–1173 PMLR
• [71] Brendan Frey、Frank Kschischang、Hans-Andrea Loeliger 与 Niclas Wiberg，“Factor graphs and algorithms”，载于 Proceedings of the Annual Allerton Conference on Communication Control and Computing 35，1997 年，第 666—680 页，Citeseer[71] Brendan Frey, Frank Kschischang, Hans-Andrea Loeliger and Niclas Wiberg “Factor graphs and algorithms” In Proceedings of the Annual Allerton Conference on Communication Control and Computing 35, 1997, pp. 666–680 Citeseer
• [72] Béla Frigyik、Santosh Srivastava 与 Maya Gupta，“An introduction to functional derivatives”，载于 Dept. Electr. Eng., Univ. Washington, Seattle, WA, Tech. Rep 1，2008 年[72] Béla Frigyik, Santosh Srivastava and Maya Gupta “An introduction to functional derivatives” In Dept. Electr. Eng., Univ. Washington, Seattle, WA, Tech. Rep 1, 2008
• [73] Roy Frostig 等，“Decomposing reverse-mode automatic differentiation”，载于 arXiv preprint arXiv:2105.09469，2021 年[73] Roy Frostig et al. “Decomposing reverse-mode automatic differentiation” In arXiv preprint arXiv:2105.09469, 2021
• [74] Walter Gautschi，《Numerical analysis》，Springer Science & Business Media，2011 年[74] Walter Gautschi “Numerical analysis” Springer Science & Business Media, 2011
• [75] Pascal Getreuer，“A survey of Gaussian convolution algorithms”，载于 Image Processing On Line 2013，2013 年，第 286—310 页[75] Pascal Getreuer “A survey of Gaussian convolution algorithms” In Image Processing On Line 2013, 2013, pp. 286–310
• [76] John Geweke，“Antithetic acceleration of Monte Carlo integration in Bayesian inference”，载于 Journal of Econometrics 38.1-2，Elsevier，1988 年，第 73—89 页[76] John Geweke “Antithetic acceleration of Monte Carlo integration in Bayesian inference” In Journal of Econometrics 38.1-2 Elsevier, 1988, pp. 73–89
• [77] Amir Gholaminejad、Kurt Keutzer 与 George Biros，“ANODE: Unconditionally Accurate Memory-Efficient Gradients for Neural ODEs”，载于 International Joint Conferences on Artificial Intelligence，2019 年[77] Amir Gholaminejad, Kurt Keutzer and George Biros “ANODE: Unconditionally Accurate Memory-Efficient Gradients for Neural ODEs” In International Joint Conferences on Artificial Intelligence, 2019
• [78] Corrado Gini，“Variabilità e mutabilità”，载于 Reprinted in Memorie di metodologica statistica (Ed. Pizetti E, Salvemini, T). Rome: Libreria Eredi Virgilio Veschi，1912 年[78] Corrado Gini “Variabilità e mutabilità” In Reprinted in Memorie di metodologica statistica (Ed. Pizetti E, Salvemini, T). Rome: Libreria Eredi Virgilio Veschi, 1912
• [79] A Girard，“A fast ‘Monte-Carlo cross-validation’ procedure for large least squares problems with noisy data”，载于 Numerische Mathematik 56，Springer，1989 年，第 1—23 页[79] A Girard “A fast ‘Monte-Carlo cross-validation’procedure for large least squares problems with noisy data” In Numerische Mathematik 56 Springer, 1989, pp. 1–23
• [80] Donald Goldfarb，“A family of variable-metric methods derived by variational means”，载于 Mathematics of computation 24.109，1970 年，第 23—26 页[80] Donald Goldfarb “A family of variable-metric methods derived by variational means” In Mathematics of computation 24.109, 1970, pp. 23–26
• [81] Aidan Gomez、Mengye Ren、Raquel Urtasun 与 Roger Grosse，“The reversible residual network: Backpropagation without storing activations”，载于 Advances in neural information processing systems 30，2017 年[81] Aidan Gomez, Mengye Ren, Raquel Urtasun and Roger Grosse “The reversible residual network: Backpropagation without storing activations” In Advances in neural information processing systems 30, 2017
• [82] Alex Graves、Greg Wayne 与 Ivo Danihelka，“Neural turing machines”，载于 arXiv preprint arXiv:1410.5401，2014 年[82] Alex Graves, Greg Wayne and Ivo Danihelka “Neural turing machines” In arXiv preprint arXiv:1410.5401, 2014
• [83] Dorothy Greig、Bruce Porteous 与 Allan Seheult，“Exact maximum a posteriori estimation for binary images”，载于 Journal of the Royal Statistical Society Series B: Statistical Methodology 51.2，Oxford University Press，1989 年，第 271—279 页[83] Dorothy Greig, Bruce Porteous and Allan Seheult “Exact maximum a posteriori estimation for binary images” In Journal of the Royal Statistical Society Series B: Statistical Methodology 51.2 Oxford University Press, 1989, pp. 271–279
• [84] Andreas Griewank，“Achieving logarithmic growth of temporal and spatial complexity in reverse automatic differentiation”，载于 Optimization Methods and Software 1.1，Taylor & Francis，1992 年，第 35—54 页，DOI: 10.1080/10556789208805505[84] Andreas Griewank “Achieving logarithmic growth of temporal and spatial complexity in reverse automatic differentiation” In Optimization Methods and Software 1.1 Taylor & Francis, 1992, pp. 35–54 DOI: 10.1080/10556789208805505
• [85] Andreas Griewank，"A mathematical view of automatic differentiation"，载于 Acta Numerica 12，Cambridge University Press，2003 年，第 321—398 页[85] Andreas Griewank “A mathematical view of automatic differentiation” In Acta Numerica 12 Cambridge University Press, 2003, pp. 321–398
• [86] Andreas Griewank，"Who invented the reverse mode of differentiation"，载于 Documenta Mathematica，Extra Volume ISMP 389400，2012 年[86] Andreas Griewank “Who invented the reverse mode of differentiation” In Documenta Mathematica, Extra Volume ISMP 389400, 2012
• [87] Andreas Griewank 与 Andrea Walther，"Evaluating derivatives: principles and techniques of algorithmic differentiation"，SIAM，2008 年[87] Andreas Griewank and Andrea Walther “Evaluating derivatives: principles and techniques of algorithmic differentiation” SIAM, 2008
• [88] José Grimm、Loïc Pottier 与 Nicole Rostaing-Schmidt，"Optimal time and minimum space-time product for reversing a certain class of programs"，1996 年[88] José Grimm, Loı̈c Pottier and Nicole Rostaing-Schmidt “Optimal time and minimum space-time product for reversing a certain class of programs”, 1996
• [89] Peter Grünwald 与 A. Dawid，"Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory"，载于 Annals of Statistics，2004 年，第 1367—1433 页[89] Peter Grünwald and A Dawid “Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory” In Annals of Statistics, 2004, pp. 1367–1433
• [90] Eric Hallman、Ilse Ipsen 与 Arvind Saibaba，"Monte Carlo methods for estimating the diagonal of a real symmetric matrix"，载于 SIAM Journal on Matrix Analysis and Applications 44.1，SIAM，2023 年，第 240—269 页[90] Eric Hallman, Ilse Ipsen and Arvind Saibaba “Monte Carlo methods for estimating the diagonal of a real symmetric matrix” In SIAM Journal on Matrix Analysis and Applications 44.1 SIAM, 2023, pp. 240–269
• [91] Kaiming He、Xiangyu Zhang、Shaoqing Ren 与 Jian Sun，"Deep residual learning for image recognition"，载于 Proceedings of the IEEE conference on computer vision and pattern recognition，2016 年，第 770—778 页[91] Kaiming He, Xiangyu Zhang, Shaoqing Ren and Jian Sun “Deep residual learning for image recognition” In Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778
• [92] Kyle Helfrich、Devin Willmott 与 Qiang Ye，"Orthogonal recurrent neural networks with scaled Cayley transform"，载于 International Conference on Machine Learning，2018 年，PMLR，第 1969—1978 页[92] Kyle Helfrich, Devin Willmott and Qiang Ye “Orthogonal recurrent neural networks with scaled Cayley transform” In International Conference on Machine Learning, 2018, pp. 1969–1978 PMLR
• [93] Magnus Hestenes 与 Eduard Stiefel，"Methods of conjugate gradients for solving linear systems"，NBS Washington, DC，1952 年[93] Magnus Hestenes and Eduard Stiefel “Methods of conjugate gradients for solving linear systems” NBS Washington, DC, 1952
• [94] Edwin Hewitt，"Rings of real-valued continuous functions. I"，载于 Transactions of the American Mathematical Society 64.1，1948 年，第 45—99 页[94] Edwin Hewitt “Rings of real-valued continuous functions. I” In Transactions of the American Mathematical Society 64.1, 1948, pp. 45–99
• [95] Takeyuki Hida 与 Masuyuki Hitsuda，"Gaussian processes"，American Mathematical Soc.，1976 年[95] Takeyuki Hida and Masuyuki Hitsuda “Gaussian processes” American Mathematical Soc., 1976
• [96] Jean-Baptiste Hiriart-Urruty 与 Claude Lemaréchal，"Convex analysis and minimization algorithms II"，Springer science & business media，1993 年[96] Jean-Baptiste Hiriart-Urruty and Claude Lemaréchal “Convex analysis and minimization algorithms II” Springer science & business media, 1993
• [97] Michael Hutchinson，"A stochastic estimator of the trace of the influence matrix for Laplacian smoothing splines"，载于 Communications in Statistics-Simulation and Computation 18.3，Taylor & Francis，1989 年，第 1059—1076 页[97] Michael Hutchinson “A stochastic estimator of the trace of the influence matrix for Laplacian smoothing splines” In Communications in Statistics-Simulation and Computation 18.3 Taylor & Francis, 1989, pp. 1059–1076
• [98] Takeo Imai，"Where did "differentiable programming" come from?"，2019 年，URL：https://medium.com/@bonotake/where-did-differentiable-programming-come-from-27b385fb6d6d[98] Takeo Imai “Where did “differentiable programming” come from?”, 2019 URL: https://medium.com/@bonotake/where-did-differentiable-programming-come-from-27b385fb6d6d
• [99] Sergey Ioffe 与 Christian Szegedy，"Batch normalization: Accelerating deep network training by reducing internal covariate shift"，载于 International conference on machine learning，2015 年，PMLR，第 448—456 页[99] Sergey Ioffe and Christian Szegedy “Batch normalization: Accelerating deep network training by reducing internal covariate shift” In International conference on machine learning, 2015, pp. 448–456 pmlr
• [100] Martin Jaggi，"Revisiting Frank-Wolfe: Projection-free sparse convex optimization"，载于 International conference on machine learning，2013 年，PMLR，第 427—435 页[100] Martin Jaggi “Revisiting Frank-Wolfe: Projection-free sparse convex optimization” In International conference on machine learning, 2013, pp. 427–435 PMLR
• [101] Eric Jang、Shixiang Gu 与 Ben Poole，“Categorical reparameterization with gumbel-softmax”，载于 arXiv preprint arXiv:1611.01144，2016 年[101] Eric Jang, Shixiang Gu and Ben Poole “Categorical reparameterization with gumbel-softmax” In arXiv preprint arXiv:1611.01144, 2016
• [102] Balasubramaniam Jayaram 与 Michał Baczynski，“Fuzzy Implications”，Springer Science & Business Media，2008 年[102] Balasubramaniam Jayaram and Michał Baczynski “Fuzzy Implications” Springer Science & Business Media, 2008
• [103] Sham Kakade、Shai Shalev-Shwartz 与 Ambuj Tewari，“On the duality of strong convexity and strong smoothness: Learning appl ications and matrix regularization”，载于 Tech report 2.1，2009 年，第 35 页[103] Sham Kakade, Shai Shalev-Shwartz and Ambuj Tewari “On the duality of strong convexity and strong smoothness: Learning appl ications and matrix regularization” In Tech report 2.1, 2009, pp. 35
• [104] Andrej Karpathy，“Software 2.0”，2017 年[104] Andrej Karpathy “Software 2.0”, 2017
• [105] Carl Kelley，“Iterative methods for linear and nonlinear equations”，SIAM，1995 年[105] Carl Kelley “Iterative methods for linear and nonlinear equations” SIAM, 1995
• [106] Diederik Kingma 与 Jimmy Ba，“Adam: A method for stochastic optimization”，载于 arXiv preprint arXiv:1412.6980，2014 年[106] Diederik Kingma and Jimmy Ba “Adam: A method for stochastic optimization” In arXiv preprint arXiv:1412.6980, 2014
• [107] Diederik Kingma 与 Max Welling，“Auto-encoding variational bayes”，载于 arXiv preprint arXiv:1312.6114，2013 年[107] Diederik Kingma and Max Welling “Auto-encoding variational bayes” In arXiv preprint arXiv:1312.6114, 2013
• [108] George Klir 与 Bo Yuan，“Fuzzy sets and fuzzy logic”，Prentice hall New Jersey，1995 年[108] George Klir and Bo Yuan “Fuzzy sets and fuzzy logic” Prentice hall New Jersey, 1995
• [109] Ivan Kobyzev、Simon Prince 与 Marcus Brubaker，“Normalizing flows: Introduction and ideas”，载于 stat 1050，2019 年，第 25 页[109] Ivan Kobyzev, Simon Prince and Marcus Brubaker “Normalizing flows: Introduction and ideas” In stat 1050, 2019, pp. 25
• [110] Wouter Kool、Herke van Hoof 与 Max Welling，“Buy 4 reinforce samples, get a baseline for free!”，2019 年[110] Wouter Kool, Herke van Hoof and Max Welling “Buy 4 reinforce samples, get a baseline for free!”, 2019
• [111] Justin Kreikemeyer 与 Philipp Andelfinger，“Smoothing methods for automatic differentiation across conditional branches”，载于 IEEE Access，IEEE，2023 年[111] Justin Kreikemeyer and Philipp Andelfinger “Smoothing methods for automatic differentiation across conditional branches” In IEEE Access IEEE, 2023
• [112] Emile Krieken、Jakub Tomczak 与 Annette Ten，“Storchastic: A framework for general stochastic automatic differentiation”，载于 Advances in Neural Information Processing Systems 34，2021 年，第 7574—7587 页[112] Emile Krieken, Jakub Tomczak and Annette Ten “Storchastic: A framework for general stochastic automatic differentiation” In Advances in Neural Information Processing Systems 34, 2021, pp. 7574–7587
• [113] Frederik Kunstner、Philipp Hennig 与 Lukas Balles，“Limitations of the empirical Fisher approximation for natural gradient descent”，载于 Advances in neural information processing systems 32，2019 年[113] Frederik Kunstner, Philipp Hennig and Lukas Balles “Limitations of the empirical Fisher approximation for natural gradient descent” In Advances in neural information processing systems 32, 2019
• [114] John Lafferty、Andrew McCallum 与 Fernando Pereira，“Conditional random fields: Probabilistic models for segmenting and labeling sequence data”，2001 年[114] John Lafferty, Andrew McCallum and Fernando Pereira “Conditional random fields: Probabilistic models for segmenting and labeling sequence data”, 2001
• [115] Guanghui Lan，“An optimal method for stochastic composite optimization”，载于 Mathematical Programming 133.1-2，Springer，2012 年，第 365—397 页[115] Guanghui Lan “An optimal method for stochastic composite optimization” In Mathematical Programming 133.1-2 Springer, 2012, pp. 365–397
• [116] Yann LeCun，“A theoretical framework for back-propagation”，载于 Proceedings of the 1988 connectionist models summer school 1，1988 年，第 21—28 页[116] Yann LeCun “A theoretical framework for back-propagation” In Proceedings of the 1988 connectionist models summer school 1, 1988, pp. 21–28
• [117] Yann LeCun，“Deep Learning est mort. Vive Differentiable Programming!”，2018 年[117] Yann LeCun “Deep Learning est mort. Vive Differentiable Programming!”, 2018
• [118] Kenneth Levenberg，“A method for the solution of certain non-linear problems in least squares”，载于 Quarterly of applied mathematics 2.2，1944 年，第 164—168 页[118] Kenneth Levenberg “A method for the solution of certain non-linear problems in least squares” In Quarterly of applied mathematics 2.2, 1944, pp. 164–168
• [119] Dong Liu 与 Jorge Nocedal，“On the limited memory method for large scale optimization”，载于 Mathematical Programming 45，1989 年，第 503—528 页[119] Dong. Liu and Jorge Nocedal “On the limited memory method for large scale optimization” In Mathematical Programming 45, 1989, pp. 503–528
• [120] Hong Liu 等，“Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”，载于 arXiv preprint arXiv:2305.14342，2023 年[120] Hong Liu et al. “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training” In arXiv preprint arXiv:2305.14342, 2023
• [121] H-A Loeliger，“An introduction to factor graphs”，载于 IEEE Signal Processing Magazine 21.1，IEEE，2004 年，第 28—41 页[121] H-A Loeliger “An introduction to factor graphs” In IEEE Signal Processing Magazine 21.1 IEEE, 2004, pp. 28–41
• [122] Ilya Loshchilov 与 Frank Hutter，“SGDR: Stochastic gradient descent with warm restarts”，载于 International Conference on Learning Representations，2016 年[122] Ilya Loshchilov and Frank Hutter “SGDR: Stochastic gradient descent with warm restarts” In International Conference on Learning Representations, 2016
• [123] Yves Lucet，“Faster than the fast Legendre transform, the linear-time Legendre transform”，载于 Numerical Algorithms 16，Springer，1997 年，第 171—185 页[123] Yves Lucet “Faster than the fast Legendre transform, the linear-time Legendre transform” In Numerical Algorithms 16 Springer, 1997, pp. 171–185
• [124] Dougal Maclaurin、David Duvenaud 与 Ryan Adams，“Autograd: Effortless gradients in numpy”，载于 ICML 2015 AutoML workshop 238.5，2015 年[124] Dougal Maclaurin, David Duvenaud and Ryan Adams “Autograd: Effortless gradients in numpy” In ICML 2015 AutoML workshop 238.5, 2015
• [125] Chris Maddison、Andriy Mnih 与 Yee Teh，“The concrete distribution: A continuous relaxation of discrete random variables”，载于 arXiv preprint arXiv:1611.00712，2016 年[125] Chris Maddison, Andriy Mnih and Yee Teh “The concrete distribution: A continuous relaxation of discrete random variables” In arXiv preprint arXiv:1611.00712, 2016
• [126] Donald Marquardt，“An algorithm for least-squares estimation of nonlinear parameters”，载于 Journal of the society for Industrial and Applied Mathematics 11.2，SIAM，1963 年，第 431—441 页[126] Donald Marquardt “An algorithm for least-squares estimation of nonlinear parameters” In Journal of the society for Industrial and Applied Mathematics 11.2 SIAM, 1963, pp. 431–441
• [127] James Martens，“New insights and perspectives on the natural gradient method”，载于 Journal of Machine Learning Research 21.1，JMLRORG，2020 年，第 5776—5851 页[127] James Martens “New insights and perspectives on the natural gradient method” In Journal of Machine Learning Research 21.1 JMLRORG, 2020, pp. 5776–5851
• [128] James Martens 与 Roger Grosse，“Optimizing neural networks with Kronecker-factored approximate curvature”，载于 International conference on machine learning，2015 年，第 2408—2417 页[128] James Martens and Roger Grosse “Optimizing neural networks with Kronecker-factored approximate curvature” In International conference on machine learning, 2015, pp. 2408–2417
• [129] Andre Martins 与 Ramon Astudillo，“From softmax to sparsemax: A sparse model of attention and multi-label classification”，载于 International conference on machine learning，2016 年，第 1614—1623 页，PMLR[129] Andre Martins and Ramon Astudillo “From softmax to sparsemax: A sparse model of attention and multi-label classification” In International conference on machine learning, 2016, pp. 1614–1623 PMLR
• [130] Joaquim Martins、Peter Sturdza 与 Juan Alonso，“The complex-step derivative approximation”，载于 ACM Transactions on Mathematical Software（TOMS）29.3，ACM New York, NY, USA，2003 年，第 245—262 页[130] Joaquim Martins, Peter Sturdza and Juan Alonso “The complex-step derivative approximation” In ACM Transactions on Mathematical Software (TOMS) 29.3 ACM New York, NY, USA, 2003, pp. 245–262
• [131] Jan-Willem van Meent、Brooks Paige、Hongseok Yang 与 Frank Wood，“An introduction to probabilistic programming”，载于 arXiv preprint arXiv:1809.10756，2018 年[131] Jan-Willem van Meent, Brooks Paige, Hongseok Yang and Frank Wood “An introduction to probabilistic programming” In arXiv preprint arXiv:1809.10756, 2018
• [132] Arthur Mensch 与 Mathieu Blondel，“Differentiable dynamic programming for structured prediction and attention”，载于 International Conference on Machine Learning，2018 年，第 3462—3471 页，PMLR[132] Arthur Mensch and Mathieu Blondel “Differentiable dynamic programming for structured prediction and attention” In International Conference on Machine Learning, 2018, pp. 3462–3471 PMLR
• [133] Florian Messerer、Katrin Baumgärtner 与 Moritz Diehl，“Survey of sequential convex programming and generalized Gauss-Newton methods”，载于 ESAIM: Proceedings and Surveys 71，EDP Sciences，2021 年，第 64—88 页[133] Florian Messerer, Katrin Baumgärtner and Moritz Diehl “Survey of sequential convex programming and generalized Gauss-Newton methods” In ESAIM: Proceedings and Surveys 71 EDP Sciences, 2021, pp. 64–88
• [134] Raphael Meyer、Cameron Musco、Christopher Musco 与 David Woodruff，“Hutch++: Optimal stochastic trace estimation”，载于 Symposium on Simplicity in Algorithms（SOSA），2021 年，第 142—155 页，SIAM。[134] Raphael Meyer, Cameron Musco, Christopher Musco and David Woodruff “Hutch++: Optimal stochastic trace estimation” In Symposium on Simplicity in Algorithms (SOSA), 2021, pp. 142–155 SIAM
• [135] Christian Michelot，“A finite algorithm for finding the projection of a point onto the canonical simplex of $\mathbb{R}^{n}$”，载于 Journal of Optimization Theory and Applications 50.1，1986 年，第 195—200 页。[135] Christian Michelot “A finite algorithm for finding the projection of a point onto the canonical simplex of $\mathbb{R}^{n}$” In Journal of Optimization Theory and Applications 50.1, 1986, pp. 195–200
• [136] Shakir Mohamed、Mihaela Rosca、Michael Figurnov 与 Andriy Mnih，“Monte carlo gradient estimation in machine learning”，载于 The Journal of Machine Learning Research 21.1，JMLRORG，2020 年，第 5183—5244 页。[136] Shakir Mohamed, Mihaela Rosca, Michael Figurnov and Andriy Mnih “Monte carlo gradient estimation in machine learning” In The Journal of Machine Learning Research 21.1 JMLRORG, 2020, pp. 5183–5244
• [137] Mehryar Mohri、Fernando Pereira 与 Michael Riley，“Speech recognition with weighted finite-state transducers”，载于 Springer Handbook of Speech Processing，Springer，2008 年，第 559—584 页。[137] Mehryar Mohri, Fernando Pereira and Michael Riley “Speech recognition with weighted finite-state transducers” In Springer Handbook of Speech Processing Springer, 2008, pp. 559–584
• [138] Jacques Morgenstern，“How to compute fast a function and all its derivatives: A variation on the theorem of Baur-Strassen”，载于 ACM SIGACT News 16.4，ACM New York, NY, USA，1985 年，第 60—62 页。[138] Jacques Morgenstern “How to compute fast a function and all its derivatives: A variation on the theorem of Baur-Strassen” In ACM SIGACT News 16.4 ACM New York, NY, USA, 1985, pp. 60–62
• [139] Charles Morrey，Multiple integrals in the calculus of variations，Springer Science & Business Media，2009 年。[139] Charles Morrey “Multiple integrals in the calculus of variations” Springer Science & Business Media, 2009
• [140] Kevin Murphy，Probabilistic Machine Learning: An introduction，MIT Press，2022 年，URL：http://probml.github.io/book1。[140] Kevin. Murphy “Probabilistic Machine Learning: An introduction” MIT Press, 2022 URL: http://probml.github.io/book1
• [141] Kevin Murphy，Probabilistic Machine Learning: Advanced Topics，MIT Press，2023 年，URL：http://probml.github.io/book2。[141] Kevin. Murphy “Probabilistic Machine Learning: Advanced Topics” MIT Press, 2023 URL: http://probml.github.io/book2
• [142] Ulrich Mutze，“An asynchronous leapfrog method II”，载于 arXiv preprint arXiv:1311.6602，2013 年。[142] Ulrich Mutze “An asynchronous leapfrog method II” In arXiv preprint arXiv:1311.6602, 2013
• [143] Arkadi Nemirovski 与 David Yudin，Problem complexity and method efficiency in optimization，Wiley-Interscience，1983 年。[143] Arkadi Nemirovski and David Yudin “Problem complexity and method efficiency in optimization” Wiley-Interscience, 1983
• [144] Yu Nesterov，“Smooth minimization of non-smooth functions”，载于 Mathematical programming 103，Springer，2005 年，第 127—152 页。[144] Yu Nesterov “Smooth minimization of non-smooth functions” In Mathematical programming 103 Springer, 2005, pp. 127–152
• [145] Yu Nesterov，“Modified Gauss–Newton scheme with worst case guarantees for global performance”，载于 Optimisation methods and software 22.3，Taylor & Francis，2007 年，第 469—483 页。[145] Yu Nesterov “Modified Gauss–Newton scheme with worst case guarantees for global performance” In Optimisation methods and software 22.3 Taylor & Francis, 2007, pp. 469–483
• [146] Yurii Nesterov，Lectures on convex optimization，Springer，2018 年。[146] Yurii Nesterov “Lectures on convex optimization” Springer, 2018
• [147] Yurii Nesterov 与 Vladimir Spokoiny，“Random gradient-free minimization of convex functions”，载于 Foundations of Computational Mathematics 17，Springer，2017 年，第 527—566 页。[147] Yurii Nesterov and Vladimir Spokoiny “Random gradient-free minimization of convex functions” In Foundations of Computational Mathematics 17 Springer, 2017, pp. 527–566
• [148] Christopher Olah，“Neural networks, types, and functional programming”，2015 年，URL：https://colah.github.io/posts/2015-09-NN-Types-FP/。[148] Christopher Olah “Neural networks, types, and functional programming”, 2015 URL: https://colah.github.io/posts/2015-09-NN-Types-FP/
• [149] George Papamakarios 等，“Normalizing flows for probabilistic modeling and inference”，载于 The Journal of Machine Learning Research 22.1，JMLRORG，2021 年，第 2617—2680 页。[149] George Papamakarios et al. “Normalizing flows for probabilistic modeling and inference” In The Journal of Machine Learning Research 22.1 JMLRORG, 2021, pp. 2617–2680
• [150] Neal Parikh 与 Stephen Boyd，“Proximal algorithms”，载于 Foundations and Trends® in Optimization 1.3，Now Publishers, Inc.，2014 年，第 127—239 页。[150] Neal Parikh and Stephen Boyd “Proximal algorithms” In Foundations and trends® in Optimization 1.3 Now Publishers, Inc., 2014, pp. 127–239
• [151] Adam Paszke 等，“PyTorch: An Imperative Style, High-Performance Deep Learning Library”，载于 Advances in Neural Information Processing Systems 32，2019 年，第 8024—8035 页。[151] Adam Paszke et al. “PyTorch: An Imperative Style, High-Performance Deep Learning Library” In Advances in Neural Information Processing Systems 32, 2019, pp. 8024–8035
• [152] Max Paulus 等，“Gradient estimation with stochastic softmax tricks”，载于 Advances in Neural Information Processing Systems 33，2020 年，第 5691—5704 页。[152] Max Paulus et al. “Gradient estimation with stochastic softmax tricks” In Advances in Neural Information Processing Systems 33, 2020, pp. 5691–5704
• [153] Felix Petersen、Christian Borgelt、Hilde Kuehne 与 Oliver Deussen，“Learning with algorithmic supervision via continuous relaxations”，载于 Advances in Neural Information Processing Systems 34，2021 年，第 16520—16531 页。[153] Felix Petersen, Christian Borgelt, Hilde Kuehne and Oliver Deussen “Learning with algorithmic supervision via continuous relaxations” In Advances in Neural Information Processing Systems 34, 2021, pp. 16520–16531
• [154] Gabriel Peyré，“Mathematical foundations of data sciences”，载于 Rn 1，2020 年，第 2 页。[154] Gabriel Peyré “Mathematical foundations of data sciences” In Rn 1, 2020, pp. 2
• [155] Gabriel Peyré 与 Marco Cuturi，“Computational optimal transport: With applications to data science”，载于 Foundations and Trends® in Machine Learning 11.5-6，Now Publishers, Inc.，2019 年，第 355—607 页。[155] Gabriel Peyré and Marco Cuturi “Computational optimal transport: With applications to data science” In Foundations and Trends® in Machine Learning 11.5-6 Now Publishers, Inc., 2019, pp. 355–607
• [156] Gordon Plotkin，“Some Principles of Differential Programming Languages”，2018 年，URL：https://popl18.sigplan.org/details/POPL-2018-papers/76/Some-Principles-of-Differential-Programming-Languages。[156] Gordon Plotkin “Some Principles of Differential Programming Languages”, 2018 URL: https://popl18.sigplan.org/details/POPL-2018-papers/76/Some-Principles-of-Differential-Programming-Languages
• [157] Sara Pollock 与 Leo Rebholz，“Anderson acceleration for contractive and noncontractive operators”，载于 IMA Journal of Numerical Analysis 41.4，Oxford University Press，2021 年，第 2841—2872 页。[157] Sara Pollock and Leo Rebholz “Anderson acceleration for contractive and noncontractive operators” In IMA Journal of Numerical Analysis 41.4 Oxford University Press, 2021, pp. 2841–2872
• [158] Boris Polyak，“Gradient methods for the minimisation of functionals”，载于 USSR Computational Mathematics and Mathematical Physics 3.4，Elsevier，1963 年，第 864—878 页。[158] Boris Polyak “Gradient methods for the minimisation of functionals” In USSR Computational Mathematics and Mathematical Physics 3.4 Elsevier, 1963, pp. 864–878
• [159] Boris Polyak，“Some methods of speeding up the convergence of iteration methods”，载于 USSR Computational Mathematics and Mathematical Physics 4.5，Elsevier，1964 年，第 1—17 页。[159] Boris Polyak “Some methods of speeding up the convergence of iteration methods” In Ussr computational mathematics and mathematical physics 4.5 Elsevier, 1964, pp. 1–17
• [160] Lev Pontryagin，“The mathematical theory of optimal processes and differential games”，载于 Trudy Mat. Inst. Steklov 169，1985 年，第 119—158 页。[160] Lev Pontryagin “The mathematical theory of optimal processes and differential games” In Trudy Mat. Inst. Steklov 169, 1985, pp. 119–158
• [161] Ofir Press 与 Lior Wolf，“Using the output embedding to improve language models”，载于 arXiv preprint arXiv:1608.05859，2016 年。[161] Ofir Press and Lior Wolf “Using the output embedding to improve language models” In arXiv preprint arXiv:1608.05859, 2016
• [162] Lawrence Rabiner，“A tutorial on hidden Markov models and selected applications in speech recognition”，载于 Proceedings of the IEEE 77.2，IEEE，1989 年，第 257—286 页。[162] Lawrence Rabiner “A tutorial on hidden Markov models and selected applications in speech recognition” In Proceedings of the IEEE 77.2 Ieee, 1989, pp. 257–286
• [163] Hans Rademacher，“Über partielle und totale differenzierbarkeit von Funktionen mehrerer Variabeln und über die Transformation der Doppelintegrale”，载于 Mathematische Annalen 79.4，Springer，1919 年，第 340—359 页。[163] Hans Rademacher “Über partielle und totale differenzierbarkeit von Funktionen mehrerer Variabeln und über die Transformation der Doppelintegrale” In Mathematische Annalen 79.4 Springer, 1919, pp. 340–359
• [164] Alexey Radul 等，“You only linearize once: Tangents transpose to gradients”，载于 arXiv preprint arXiv:2204.10923，2022 年。[164] Alexey Radul et al. “You only linearize once: Tangents transpose to gradients” In arXiv preprint arXiv:2204.10923, 2022
• [165] Ali Rahimi、Benjamin Recht，《Random features for large-scale kernel machines》，载《Advances in neural information processing systems》第 20 卷，2007 年。[165] Ali Rahimi and Benjamin Recht “Random features for large-scale kernel machines” In Advances in neural information processing systems 20, 2007
• [166] Benjamin Recht，《Mates of Costate》，2016 年。[166] Benjamin Recht “Mates of Costate”, 2016
• [167] Benjamin Recht、Roy Frostig，《Nesterov’s Punctuated Equilibrium》，2017 年。[167] Benjamin Recht and Roy Frostig “Nesterov’s Punctuated Equilibrium”, 2017
• [168] Danilo Rezende、Shakir Mohamed、Daan Wierstra，《Stochastic backpropagation and approximate inference in deep generative models》，载《International conference on machine learning》，PMLR，2014 年，第 1278—1286 页。[168] Danilo Rezende, Shakir Mohamed and Daan Wierstra “Stochastic backpropagation and approximate inference in deep generative models” In International conference on machine learning, 2014, pp. 1278–1286 PMLR
• [169] R. Rockafellar、Roger-B. Wets，《Variational analysis》，Springer Science & Business Media，2009 年。[169] R Rockafellar and Roger-B Wets “Variational analysis” Springer Science & Business Media, 2009
• [170] Omar Rodriguez、Jorge Lopez，《A semiotic reflection on the didactics of the chain rule》，载《The Mathematics Enthusiast》第 7 卷第 2 期，2010 年，第 321—332 页。[170] Omar Rodriguez and Jorge Lopez “A semiotic reflection on the didactics of the chain rule” In The Mathematics Enthusiast 7.2, 2010, pp. 321–332
• [171] Vincent Roulet、Zaid Harchaoui，《Differentiable programming à la Moreau》，载《ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing（ICASSP）》，IEEE，2022 年，第 3498—3502 页。[171] Vincent Roulet and Zaid Harchaoui “Differentiable programming à la Moreau” In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022, pp. 3498–3502 IEEE
• [172] Youcef Saad、Martin Schultz，《GMRES: A generalized minimal residual algorithm for solving nonsymmetric linear systems》，载《SIAM Journal on scientific and statistical computing》第 7 卷第 3 期，SIAM，1986 年，第 856—869 页。[172] Youcef Saad and Martin Schultz “GMRES: A generalized minimal residual algorithm for solving nonsymmetric linear systems” In SIAM Journal on scientific and statistical computing 7.3 SIAM, 1986, pp. 856–869
• [173] Tim Salimans 等，《Evolution strategies as a scalable alternative to reinforcement learning》，载 arXiv preprint arXiv:1703.03864，2017 年。[173] Tim Salimans et al. “Evolution strategies as a scalable alternative to reinforcement learning” In arXiv preprint arXiv:1703.03864, 2017
• [174] Michael Sander、Pierre Ablin、Mathieu Blondel、Gabriel Peyré，《Momentum residual neural networks》，载《International Conference on Machine Learning》，PMLR，2021 年，第 9276—9287 页。[174] Michael Sander, Pierre Ablin, Mathieu Blondel and Gabriel Peyré “Momentum residual neural networks” In International Conference on Machine Learning, 2021, pp. 9276–9287 PMLR
• [175] Michael Sander、Pierre Ablin、Mathieu Blondel、Gabriel Peyré，《Momentum residual neural networks》，载《International Conference on Machine Learning》，PMLR，2021 年，第 9276—9287 页。[175] Michael Sander, Pierre Ablin, Mathieu Blondel and Gabriel Peyré “Momentum residual neural networks” In International Conference on Machine Learning, 2021, pp. 9276–9287 PMLR
• [176] FE Satterthwaite，《Generalized poisson distribution》，载《The Annals of Mathematical Statistics》第 13 卷第 4 期，JSTOR，1942 年，第 410—417 页。[176] FE Satterthwaite “Generalized poisson distribution” In The Annals of Mathematical Statistics 13.4 JSTOR, 1942, pp. 410–417
• [177] Imanol Schlag、Kazuki Irie、Jürgen Schmidhuber，《Linear transformers are secretly fast weight programmers》，载《International Conference on Machine Learning》，PMLR，2021 年，第 9355—9366 页。[177] Imanol Schlag, Kazuki Irie and Jürgen Schmidhuber “Linear transformers are secretly fast weight programmers” In International Conference on Machine Learning, 2021, pp. 9355–9366 PMLR
• [178] Bernhard Schölkopf、Alexander Smola，《Learning with kernels: support vector machines, regularization, optimization, and beyond》，MIT press，2002 年。[178] Bernhard Schölkopf and Alexander Smola “Learning with kernels: support vector machines, regularization, optimization, and beyond” MIT press, 2002
• [179] John Schulman、Nicolas Heess、Theophane Weber、Pieter Abbeel，《Gradient estimation using stochastic computation graphs》，载《Advances in neural information processing systems》第 28 卷，2015 年。[179] John Schulman, Nicolas Heess, Theophane Weber and Pieter Abbeel “Gradient estimation using stochastic computation graphs” In Advances in neural information processing systems 28, 2015
• [180] J. Schwartz，《The formula for change in variables in a multiple integral》，载《The American Mathematical Monthly》第 61 卷第 2 期，Taylor & Francis，1954 年，第 81—85 页。[180] J Schwartz “The formula for change in variables in a multiple integral” In The American Mathematical Monthly 61.2 Taylor & Francis, 1954, pp. 81–85
• [181] Hermann Schwarz，《Communication》，载《Archives des Sciences Physiques et Naturelles》第 48 卷，1873 年，第 38—44 页。[181] Hermann Schwarz “Communication” In Archives des Sciences Physiques et Naturelles 48, 1873, pp. 38–44
• [182] Shubhabrata Sengupta、Mark Harris、Michael Garland 与 John Owens，《面向众核 GPU 的高效并行 scan 算法》，2010 年。[182] Shubhabrata Sengupta, Mark Harris, Michael Garland and John Owens “Efficient Parallel Scan Algorithms for Manycore GPUs.”, 2010
• [183] David Shanno，《用于函数极小化的拟牛顿法的条件化》，载《Mathematics of computation》第 24 卷第 111 期，1970 年，第 647—656 页。[183] David Shanno “Conditioning of quasi-Newton methods for function minimization” In Mathematics of computation 24.111, 1970, pp. 647–656
• [184] Claude Shannon，《通信的数学理论》，载《The Bell system technical journal》第 27 卷第 3 期，Nokia Bell Labs，1948 年，第 379—423 页。[184] Claude Shannon “A mathematical theory of communication” In The Bell system technical journal 27.3 Nokia Bell Labs, 1948, pp. 379–423
• [185] John Shawe-Taylor 与 Nello Cristianini，《用于模式分析的核方法》，Cambridge university press，2004 年。[185] John Shawe-Taylor and Nello Cristianini “Kernel methods for pattern analysis” Cambridge university press, 2004
• [186] William Squire 与 George Trapp，《使用复变量估计实函数的导数》，载《SIAM review》第 40 卷第 1 期，SIAM，1998 年，第 110—112 页。[186] William Squire and George Trapp “Using complex variables to estimate derivatives of real functions” In SIAM review 40.1 SIAM, 1998, pp. 110–112
• [187] Josef Stoer 等，《数值分析导论》，Springer，1980 年。[187] Josef Stoer et al. “Introduction to numerical analysis” Springer, 1980
• [188] Philipp Stumm 与 Andrea Walther，《最优在线检查点的新算法》，载《SIAM Journal on Scientific Computing》第 32 卷第 2 期，SIAM，2010 年，第 836—854 页。[188] Philipp Stumm and Andrea Walther “New algorithms for optimal online checkpointing” In SIAM Journal on Scientific Computing 32.2 SIAM, 2010, pp. 836–854
• [189] Jianlin Su 等，《Roformer：采用旋转位置嵌入的增强 Transformer》，载《Neurocomputing》第 568 卷，Elsevier，2024 年，第 127063 页。[189] Jianlin Su et al. “Roformer: Enhanced transformer with rotary position embedding” In Neurocomputing 568 Elsevier, 2024, pp. 127063
• [190] Danica Sutherland 与 Jeff Schneider，《论随机傅里叶特征的误差》，载《arXiv preprint arXiv:1506.02785》，2015 年。[190] Danica Sutherland and Jeff Schneider “On the error of random Fourier features” In arXiv preprint arXiv:1506.02785, 2015
• [191] Ilya Sutskever、James Martens、George Dahl 与 Geoffrey Hinton，《论初始化与动量在深度学习中的重要性》，载《International conference on machine learning》，PMLR，2013 年，第 1139—1147 页。[191] Ilya Sutskever, James Martens, George Dahl and Geoffrey Hinton “On the importance of initialization and momentum in deep learning” In International conference on machine learning, 2013, pp. 1139–1147 PMLR
• [192] Charles Sutton 与 Andrew McCallum，《条件随机场导论》，载《Foundations and Trends® in Machine Learning》第 4 卷第 4 期，Now Publishers, Inc.，2012 年，第 267—373 页。[192] Charles Sutton and Andrew McCallum “An introduction to conditional random fields” In Foundations and Trends® in Machine Learning 4.4 Now Publishers, Inc., 2012, pp. 267–373
• [193] Richard Sutton、David McAllester、Satinder Singh 与 Yishay Mansour，《带函数近似的强化学习策略梯度方法》，载《Advances in neural information processing systems》第 12 卷，1999 年。[193] Richard Sutton, David McAllester, Satinder Singh and Yishay Mansour “Policy gradient methods for reinforcement learning with function approximation” In Advances in neural information processing systems 12, 1999
• [194] Michael Taylor，《微分形式与多重积分的变量替换公式》，载《Journal of mathematical analysis and applications》第 268 卷第 1 期，Elsevier，2002 年，第 378—383 页。[194] Michael Taylor “Differential forms and the change of variable formula for multiple integrals” In Journal of mathematical analysis and applications 268.1 Elsevier, 2002, pp. 378–383
• [195] Robert Tibshirani，《通过 lasso 进行回归收缩与变量选择》，载《Journal of the Royal Statistical Society: Series B (Methodological)》第 58 卷第 1 期，Wiley Online Library，1996 年，第 267—288 页。[195] Robert Tibshirani “Regression shrinkage and selection via the lasso” In Journal of the Royal Statistical Society: Series B (Methodological) 58.1 Wiley Online Library, 1996, pp. 267–288
• [196] Jean-Pierre Tignol，《Galois 的代数方程理论》，World Scientific Publishing Company，2015 年。[196] Jean-Pierre Tignol “Galois’ theory of algebraic equations” World Scientific Publishing Company, 2015
• [197] Constantino Tsallis，《Boltzmann-Gibbs 统计的一种可能推广》，载《Journal of statistical physics》第 52 卷，Springer，1988 年，第 479—487 页。[197] Constantino Tsallis “Possible generalization of Boltzmann-Gibbs statistics” In Journal of statistical physics 52 Springer, 1988, pp. 479–487
• [198] Emile van Krieken，《神经符号学习系统中的优化》，2024 年。[198] Emile van Krieken “Optimisation in Neurosymbolic Learning Systems”, 2024
• [199] Ashish Vaswani 等，《注意力就是你所需要的一切》，载《Advances in neural information processing systems》第 30 卷，2017 年。[199] Ashish Vaswani et al. “Attention is all you need” In Advances in neural information processing systems 30, 2017
• [200] Sharan Vaswani 等，“Painless stochastic gradient: Interpolation, line-search, and convergence rates”，载《Advances in Neural Information Processing Systems》第 32 卷，2019 年。[200] Sharan Vaswani et al. “Painless stochastic gradient: Interpolation, line-search, and convergence rates” In Advances in neural information processing systems 32, 2019
• [201] Sergio Verdu 与 H. Poor，“Abstract dynamic programming models under commutativity conditions”，载《SIAM Journal on Control and Optimization》第 25 卷第 4 期，SIAM，1987 年，第 990—1006 页。[201] Sergio Verdu and H Poor “Abstract dynamic programming models under commutativity conditions” In SIAM Journal on Control and Optimization 25.4 SIAM, 1987, pp. 990–1006
• [202] Paul Vicol、Luke Metz 与 Jascha Sohl-Dickstein，“Unbiased gradient estimation in unrolled computation graphs with persistent evolution strategies”，载《International Conference on Machine Learning》，2021 年，第 10553—10563 页，PMLR。[202] Paul Vicol, Luke Metz and Jascha Sohl-Dickstein “Unbiased gradient estimation in unrolled computation graphs with persistent evolution strategies” In International Conference on Machine Learning, 2021, pp. 10553–10563 PMLR
• [203] Pauli Virtanen 等，“SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python”，载《Nature Methods》第 17 卷，2020 年，第 261—272 页。[203] Pauli Virtanen et al. “SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python” In Nature Methods 17, 2020, pp. 261–272
• [204] Andrew Viterbi，“Error bounds for convolutional codes and an asymptotically optimum decoding algorithm”，载《IEEE Transactions on Information Theory》第 13 卷第 2 期，IEEE，1967 年，第 260—269 页。[204] Andrew Viterbi “Error bounds for convolutional codes and an asymptotically optimum decoding algorithm” In IEEE transactions on Information Theory 13.2 IEEE, 1967, pp. 260–269
• [205] H. Vorst 与 H. van Vorst，“Bi-CGSTAB: A Fast and Smoothly Converging Variant of Bi-CG for the Solution of Nonsymmetric Linear Systems”，载《SIAM Journal on Scientific and Statistical Computing》第 13 卷第 2 期，1992 年，第 631—644 页，URL：http://dx.doi.org/10.1137/0913035。[205] H Vorst and H van Vorst “Bi-CGSTAB: A Fast and Smoothly Converging Variant of Bi-CG for the Solution of Nonsymmetric Linear Systems” In SIAM Journal on Scientific and Statistical Computing 13.2, 1992, pp. 631–644 URL: http://dx.doi.org/10.1137/0913035
• [206] Martin Wainwright 与 Michael Jordan，“Graphical models, exponential families, and variational inference”，载《Foundations and Trends® in Machine Learning》第 1 卷第 1—2 期，Now Publishers, Inc.，2008 年，第 1—305 页。[206] Martin Wainwright and Michael Jordan “Graphical models, exponential families, and variational inference” In Foundations and Trends® in Machine Learning 1.1–2 Now Publishers, Inc., 2008, pp. 1–305
• [207] Qiqi Wang、Parviz Moin 与 Gianluca Iaccarino，“Minimal repetition dynamic checkpointing algorithm for unsteady adjoint calculation”，载《SIAM Journal on Scientific Computing》第 31 卷第 4 期，SIAM，2009 年，第 2549—2567 页。[207] Qiqi Wang, Parviz Moin and Gianluca Iaccarino “Minimal repetition dynamic checkpointing algorithm for unsteady adjoint calculation” In SIAM Journal on Scientific Computing 31.4 SIAM, 2009, pp. 2549–2567
• [208] Colin Wei、Sham Kakade 与 Tengyu Ma，“The implicit and explicit regularization effects of dropout”，载《International Conference on Machine Learning》，2020 年，第 10181—10192 页，PMLR。[208] Colin Wei, Sham Kakade and Tengyu Ma “The implicit and explicit regularization effects of dropout” In International conference on machine learning, 2020, pp. 10181–10192 PMLR
• [209] Paul Werbos，“Backpropagation through time: what it does and how to do it”，载《Proceedings of the IEEE》第 78 卷第 10 期，IEEE，1990 年，第 1550—1560 页。[209] Paul Werbos “Backpropagation through time: what it does and how to do it” In Proceedings of the IEEE 78.10 IEEE, 1990, pp. 1550–1560
• [210] Paul Werbos，《The roots of backpropagation: from ordered derivatives to neural networks and political forecasting》，John Wiley & Sons，1994 年。[210] Paul Werbos “The roots of backpropagation: from ordered derivatives to neural networks and political forecasting” John Wiley & Sons, 1994
• [211] Stephen Wright 与 Jorge Nocedal，《Numerical Optimization》，载《Springer Science》第 35 卷第 67—68 期，1999 年，第 7 页。[211] Stephen Wright and Jorge Nocedal “Numerical optimization” In Springer Science 35.67-68, 1999, pp. 7
• [212] Peng Xu、Fred Roosta 与 Michael Mahoney，“Second-order optimization for non-convex machine learning: An empirical study”，载《Proceedings of the 2020 SIAM International Conference on Data Mining》，2020 年，第 199—207 页，SIAM。[212] Peng Xu, Fred Roosta and Michael Mahoney “Second-order optimization for non-convex machine learning: An empirical study” In Proceedings of the 2020 SIAM International Conference on Data Mining, 2020, pp. 199–207 SIAM
• [213] Ming Yuan 与 Yi Lin，“Model selection and estimation in regression with grouped variables”，载《Journal of the Royal Statistical Society: Series B (Statistical Methodology)》第 68 卷第 1 期，Wiley Online Library，2006 年，第 49—67 页。[213] Ming Yuan and Yi Lin “Model selection and estimation in regression with grouped variables” In Journal of the Royal Statistical Society: Series B (Statistical Methodology) 68.1 Wiley Online Library, 2006, pp. 49–67
• [214] Aston Zhang、Zachary Lipton、Mu Li 与 Alexander Smola，“Dive into deep learning”，载 arXiv preprint arXiv:2106.11342，2021 年。[214] Aston Zhang, Zachary Lipton, Mu Li and Alexander Smola “Dive into deep learning” In arXiv preprint arXiv:2106.11342, 2021
• [215] Xingyu Zhou，“On the fenchel duality between strong convexity and lipschitz continuous gradient”，载 arXiv preprint arXiv:1803.06573，2018 年。[215] Xingyu Zhou “On the fenchel duality between strong convexity and lipschitz continuou s gradient” In arXiv preprint arXiv:1803.06573, 2018
• [216] Juntang Zhuang、Nicha Dvornek、Sekhar Tatikonda 与 James Duncan，“Mali: A memory efficient and reverse accurate integrator for neural odes”，载 arXiv preprint arXiv:2102.04668，2021 年。[216] Juntang Zhuang, Nicha Dvornek, Sekhar Tatikonda and James Duncan “Mali: A memory efficient and reverse accurate integrator for neural odes” In arXiv preprint arXiv:2102.04668, 2021
• [217] Daniel Ziegler 等，“Fine-tuning language models from human preferences”，载 arXiv preprint arXiv:1909.08593，2019 年。[217] Daniel Ziegler et al. “Fine-tuning language models from human preferences” In arXiv preprint arXiv:1909.08593, 2019