--- references: - id: AbtFisher1998 accessed: - year: 2019 month: 10 day: 2 author: - family: Abt given: Markus - family: Welch given: William J. citation-key: AbtFisher1998 container-title: Canadian Journal of Statistics DOI: 10.2307/3315678 ISSN: 1708-945X issue: '1' issued: - year: 1998 language: en page: 127-137 title: >- Fisher information and maximum-likelihood estimation of covariance parameters in Gaussian stochastic processes type: article-journal volume: '26' - id: AgarwalSecond2016 accessed: - year: 2016 month: 3 day: 11 author: - family: Agarwal given: Naman - family: Bullins given: Brian - family: Hazan given: Elad citation-key: AgarwalSecond2016 container-title: arXiv:1602.03943 [cs, stat] issued: - year: 2016 month: 2 day: 11 title: Second Order Stochastic Optimization in Linear Time type: article-journal URL: http://arxiv.org/abs/1602.03943 - id: AmariAdaptive2000 accessed: - year: 2019 month: 7 day: 19 author: - family: Amari given: Shun-ichi - family: Park given: Hyeyoung - family: Fukumizu given: Kenji citation-key: AmariAdaptive2000 container-title: Neural Computation container-title-short: Neural Computation DOI: 10.1162/089976600300015420 ISSN: 0899-7667 issue: '6' issued: - year: 2000 month: 6 day: 1 page: 1399-1409 PMID: '10935719' title: >- Adaptive Method of Realizing Natural Gradient Learning for Multilayer Perceptrons type: article-journal URL: https://www.mitpressjournals.org/doi/10.1162/089976600300015420 volume: '12' - id: AmariFisher2018 accessed: - year: 2019 month: 7 day: 19 author: - family: Amari given: Shun-ichi - family: Karakida given: Ryo - family: Oizumi given: Masafumi citation-key: AmariFisher2018 container-title: arXiv:1808.07172 [cond-mat, stat] issued: - year: 2018 month: 8 day: 21 title: Fisher Information and Natural Gradient Learning of Random Deep Networks type: article-journal URL: http://arxiv.org/abs/1808.07172 - id: AmariNatural1998 accessed: - year: 2014 month: 8 day: 30 author: - family: Amari given: Shun-ichi citation-key: AmariNatural1998 container-title: Neural Computation container-title-short: Neural Computation DOI: 10.1162/089976698300017746 ISSN: 0899-7667 issue: '2' issued: - year: 1998 month: 2 day: 1 page: 251-276 title: Natural Gradient Works Efficiently in Learning type: article-journal volume: '10' - id: ArbelKernelized2020 accessed: - year: 2023 month: 6 day: 2 author: - family: Arbel given: Michael - family: Gretton given: Arthur - family: Li given: Wuchen - family: Montufar given: Guido citation-key: ArbelKernelized2020 DOI: 10.48550/arXiv.1910.09652 issued: - year: 2020 month: 2 day: 13 number: arXiv:1910.09652 publisher: arXiv title: Kernelized Wasserstein Natural Gradient type: article URL: http://arxiv.org/abs/1910.09652 - id: ArnoldAccelerating2017 accessed: - year: 2018 month: 4 day: 27 author: - family: Arnold given: Sébastien M. R. - family: Wang given: Chunming citation-key: ArnoldAccelerating2017 container-title: arXiv:1709.05069 [cs] event-title: ICLR issued: - year: 2017 title: >- Accelerating SGD for Distributed Deep-Learning Using Approximated Hessian Matrix type: paper-conference URL: http://arxiv.org/abs/1709.05069 - id: BachNonAsymptotic2011 accessed: - year: 2014 month: 6 day: 11 author: - family: Bach given: Francis - family: Moulines given: Eric citation-key: BachNonAsymptotic2011 container-title: Advances in Neural Information Processing Systems (NIPS) event-place: Spain issued: - year: 2011 language: English page: '-' publisher-place: Spain title: >- Non-Asymptotic Analysis of Stochastic Approximation Algorithms for Machine Learning type: paper-conference URL: http://hal.archives-ouvertes.fr/hal-00608041 - id: BachNonstronglyconvex2013 author: - family: Bach given: Francis R. - family: Moulines given: Eric citation-key: BachNonstronglyconvex2013 container-title: arXiv:1306.2119 [cs, math, stat] issued: - year: 2013 month: 6 day: 10 page: 773–781 title: >- Non-strongly-convex smooth stochastic approximation with convergence rate O(1/n) type: paper-conference URL: https://arxiv.org/abs/1306.2119v1 - id: BaDistributed2016 accessed: - year: 2018 month: 4 day: 2 author: - family: Ba given: Jimmy - family: Grosse given: Roger - family: Martens given: James citation-key: BaDistributed2016 issued: - year: 2016 month: 11 day: 5 title: >- Distributed Second-Order Optimization using Kronecker-Factored Approximations type: article-journal URL: https://openreview.net/forum?id=SkkTMpjex - id: BattitiFirstand1992 accessed: - year: 2015 month: 3 day: 20 author: - family: Battiti given: Roberto citation-key: BattitiFirstand1992 container-title: Neural computation container-title-short: Neural Computation DOI: 10.1162/neco.1992.4.2.141 ISSN: 0899-7667 issue: '2' issued: - year: 1992 page: 141–166 title: >- First-and second-order methods for learning: between steepest descent and Newton's method type: article-journal URL: >- http://rtm.science.unitn.it/~battiti/archive/FirstSecondOrderMethodsForLearning.PDF volume: '4' - id: BordesSGDQN2009 accessed: - year: 2015 month: 6 day: 18 author: - family: Bordes given: Antoine - family: Bottou given: Léon - family: Gallinari given: Patrick citation-key: BordesSGDQN2009 container-title: Journal of Machine Learning Research ISSN: 1532-4435 issued: - year: 2009 month: 12 page: 1737–1754 title: 'SGD-QN: Careful Quasi-Newton Stochastic Gradient Descent' type: article-journal URL: http://jmlr.org/papers/volume10/bordes09a/bordes09a.pdf volume: '10' - id: BotevPractical2017 accessed: - year: 2023 month: 1 day: 17 author: - family: Botev given: Aleksandar - family: Ritter given: Hippolyt - family: Barber given: David citation-key: BotevPractical2017 container-title: Proceedings of the 34th International Conference on Machine Learning event-title: International Conference on Machine Learning ISSN: 2640-3498 issued: - year: 2017 month: 7 day: 17 language: en page: 557-565 publisher: PMLR title: Practical Gauss-Newton Optimisation for Deep Learning type: paper-conference URL: http://arxiv.org/abs/1706.03662 - id: BottouStochastic2012 accessed: - year: 2017 month: 10 day: 12 author: - family: Bottou given: Léon citation-key: BottouStochastic2012 collection-title: Lecture Notes in Computer Science container-title: 'Neural Networks: Tricks of the Trade' DOI: 10.1007/978-3-642-35289-8_25 ISBN: 978-3-642-35288-1 978-3-642-35289-8 issued: - year: 2012 language: en page: 421-436 publisher: Springer, Berlin, Heidelberg title: Stochastic Gradient Descent Tricks type: chapter URL: http://leon.bottou.org/publications/pdf/tricks-2012.pdf - id: ByrdStochastic2016 accessed: - year: 2020 month: 1 day: 22 author: - family: Byrd given: R. H. - family: Hansen given: S. L. - family: Nocedal given: Jorge. - family: Singer given: Y. citation-key: ByrdStochastic2016 container-title: SIAM Journal on Optimization container-title-short: SIAM J. Optim. DOI: 10.1137/140954362 ISSN: 1052-6234 issue: '2' issued: - year: 2016 month: 1 day: 1 page: 1008-1031 title: A Stochastic Quasi-Newton Method for Large-Scale Optimization type: article-journal URL: http://arxiv.org/abs/1401.7020 volume: '26' - id: ChoHessianfree2015 accessed: - year: 2018 month: 4 day: 2 author: - family: Cho given: Minhyung - family: Dhir given: Chandra Shekhar - family: Lee given: Jaehyung citation-key: ChoHessianfree2015 container-title: Advances In Neural Information Processing Systems event-title: NIPS issued: - year: 2015 month: 9 day: 11 title: >- Hessian-free Optimization for Learning Deep Multidimensional Recurrent Neural Networks type: paper-conference URL: http://arxiv.org/abs/1509.03475 - id: DangelBackPACK2019 accessed: - year: 2021 month: 8 day: 5 author: - family: Dangel given: Felix - family: Kunstner given: Frederik - family: Hennig given: Philipp citation-key: DangelBackPACK2019 container-title: International conference on learning representations event-title: International Conference on Learning Representations issued: - year: 2019 month: 9 day: 25 language: en title: 'BackPACK: Packing more into Backprop' type: paper-conference URL: https://openreview.net/forum?id=BJlrF24twB - id: DauphinIdentifying2014 author: - family: Dauphin given: Yann - family: Pascanu given: Razvan - family: Gulcehre given: Caglar - family: Cho given: Kyunghyun - family: Ganguli given: Surya - family: Bengio given: Yoshua citation-key: DauphinIdentifying2014 container-title: Advances in Neural Information Processing Systems 27 issued: - year: 2014 month: 6 day: 10 page: 2933–2941 publisher: Curran Associates, Inc. title: >- Identifying and attacking the saddle point problem in high-dimensional non-convex optimization type: paper-conference URL: http://arxiv.org/abs/1406.2572 - id: DetommasoStein2018 accessed: - year: 2022 month: 10 day: 12 author: - family: Detommaso given: Gianluca - family: Cui given: Tiangang - family: Spantini given: Alessio - family: Marzouk given: Youssef - family: Scheichl given: Robert citation-key: DetommasoStein2018 collection-title: NIPS'18 container-title: >- Proceedings of the 32nd International Conference on Neural Information Processing Systems DOI: 10.48550/arXiv.1806.03085 event-place: Red Hook, NY, USA event-title: Advances in Neural Information Processing Systems 2018 issued: - year: 2018 month: 12 day: 3 page: 9187–9197 publisher: Curran Associates Inc. publisher-place: Red Hook, NY, USA title: A Stein variational Newton method type: paper-conference URL: http://arxiv.org/abs/1806.03085 - id: EfronAssessing1978 accessed: - year: 2015 month: 6 day: 24 author: - family: Efron given: Bradley - family: Hinkley given: David V. citation-key: EfronAssessing1978 container-title: Biometrika container-title-short: Biometrika DOI: 10.1093/biomet/65.3.457 ISSN: 0006-3444, 1464-3510 issue: '3' issued: - year: 1978 month: 1 day: 12 language: en page: 457-483 title: >- Assessing the accuracy of the maximum likelihood estimator: Observed versus expected Fisher information type: article-journal URL: https://statistics.stanford.edu/sites/default/files/EFS%20NSF%20108.pdf volume: '65' - id: GravellApproximate2021 accessed: - year: 2021 month: 12 day: 8 author: - family: Gravell given: Benjamin - family: Shames given: Iman - family: Summers given: Tyler citation-key: GravellApproximate2021 container-title: arXiv:2011.14212 [cs, eess, math] issued: - year: 2021 month: 2 day: 18 language: en title: Approximate Midpoint Policy Iteration for Linear Quadratic Control type: article-journal URL: http://arxiv.org/abs/2011.14212 - id: GrosseKroneckerfactored2016 accessed: - year: 2023 month: 1 day: 17 author: - family: Grosse given: Roger - family: Martens given: James citation-key: GrosseKroneckerfactored2016 container-title: Proceedings of The 33rd International Conference on Machine Learning event-title: International Conference on Machine Learning ISSN: 1938-7228 issued: - year: 2016 month: 6 day: 11 language: en page: 573-582 publisher: PMLR title: A Kronecker-factored approximate Fisher matrix for convolution layers type: paper-conference URL: https://proceedings.mlr.press/v48/grosse16.html - id: GrosseMetrics2021 accessed: - year: 2022 month: 7 day: 25 author: - family: Grosse given: Roger citation-key: GrosseMetrics2021 container-title: CSC2541 Winter 2021 issued: - year: 2021 page: Chapter 3 title: Metrics type: chapter URL: >- https://www.cs.toronto.edu/~rgrosse/courses/csc2541_2021/readings/L03_metrics.pdf - id: HensmanFast2012 accessed: - year: 2023 month: 6 day: 2 author: - family: Hensman given: James - family: Rattray given: Magnus - family: Lawrence given: Neil citation-key: HensmanFast2012 container-title: Advances in Neural Information Processing Systems issued: - year: 2012 publisher: Curran Associates, Inc. title: Fast Variational Inference in the Conjugate Exponential Family type: paper-conference URL: >- https://proceedings.neurips.cc/paper_files/paper/2012/hash/50905d7b2216bfeccb5b41016357176b-Abstract.html volume: '25' - id: HuTraining2022 accessed: - year: 2022 month: 8 day: 11 author: - family: Hu given: Hang - family: Song given: Zhao - family: Weinstein given: Omri - family: Zhuo given: Danyang citation-key: HuTraining2022 DOI: 10.48550/arXiv.2208.04508 issued: - year: 2022 month: 8 day: 8 number: arXiv:2208.04508 publisher: arXiv title: Training Overparametrized Neural Networks in Sublinear Time type: article URL: http://arxiv.org/abs/2208.04508 - id: KakadeNatural2002 author: - family: Kakade given: Sham M citation-key: KakadeNatural2002 container-title: Advances In Neural Information Processing Systems event-title: Neural Information Processing Systems issued: - year: 2002 language: en page: '8' title: A Natural Policy Gradient type: paper-conference - id: KarakidaUnderstanding2020 accessed: - year: 2020 month: 12 day: 11 author: - family: Karakida given: Ryo - family: Osawa given: Kazuki citation-key: KarakidaUnderstanding2020 container-title: Advances in Neural Information Processing Systems issued: - year: 2020 language: en title: >- Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks type: article-journal URL: >- https://proceedings.neurips.cc//paper_files/paper/2020/hash/7b41bfa5085806dfa24b8c9de0ce567f-Abstract.html volume: '33' - id: KhanBayesian2023 accessed: - year: 2024 month: 2 day: 8 author: - family: Khan given: Mohammad Emtiyaz - family: Rue given: Håvard citation-key: KhanBayesian2023 DOI: 10.48550/arXiv.2107.04562 issued: - year: 2023 month: 6 day: 30 number: arXiv:2107.04562 publisher: arXiv title: The Bayesian Learning Rule type: article URL: http://arxiv.org/abs/2107.04562 - id: KovalevStochastic2019 accessed: - year: 2020 month: 1 day: 28 author: - family: Kovalev given: Dmitry - family: Mishchenko given: Konstantin - family: Richtárik given: Peter citation-key: KovalevStochastic2019 container-title: arXiv:1912.01597 [cs, math, stat] issued: - year: 2019 month: 12 day: 3 language: en title: >- Stochastic Newton and Cubic Newton Methods with Simple Local Linear-Quadratic Rates type: article-journal URL: http://arxiv.org/abs/1912.01597 - id: LesageLandrySecondorder2021 accessed: - year: 2021 month: 12 day: 8 author: - family: Lesage-Landry given: Antoine - family: Taylor given: Joshua A. - family: Shames given: Iman citation-key: LesageLandrySecondorder2021 container-title: IEEE Transactions on Automatic Control container-title-short: IEEE Trans. Automat. Contr. DOI: 10.1109/TAC.2020.3040372 ISSN: 0018-9286, 1558-2523, 2334-3303 issue: '10' issued: - year: 2021 month: 10 language: en page: 4866-4872 title: Second-order Online Nonconvex Optimization type: article-journal URL: http://arxiv.org/abs/2001.10114 volume: '66' - id: LjungStochastic1992 accessed: - year: 2022 month: 9 day: 5 author: - family: Ljung given: Lennart - family: Pflug given: Georg - family: Walk given: Harro citation-key: LjungStochastic1992 container-title-short: DMV Seminar vol. 17 DOI: 10.1007/978-3-0348-8609-3 event-place: Basel ISBN: 978-3-7643-2733-0 978-3-0348-8609-3 issued: - year: 1992 language: en publisher: Birkhäuser publisher-place: Basel title: Stochastic Approximation and Optimization of Random Systems type: book URL: http://publications.mfo.de/handle/mfo/500 - id: LucchiVariance2015 accessed: - year: 2015 month: 7 day: 1 author: - family: Lucchi given: Aurelien - family: McWilliams given: Brian - family: Hofmann given: Thomas citation-key: LucchiVariance2015 container-title: arXiv:1503.08316 [cs] issued: - year: 2015 month: 3 day: 28 title: A Variance Reduced Stochastic Newton Method type: article-journal URL: http://arxiv.org/abs/1503.08316 - id: LyTutorial2017 accessed: - year: 2020 month: 5 day: 24 author: - family: Ly given: Alexander - family: Marsman given: Maarten - family: Verhagen given: Josine - family: Grasman given: Raoul P. P. P. - family: Wagenmakers given: Eric-Jan citation-key: LyTutorial2017 container-title: Journal of Mathematical Psychology container-title-short: Journal of Mathematical Psychology DOI: 10.1016/j.jmp.2017.05.006 ISSN: 0022-2496 issued: - year: 2017 month: 10 day: 1 language: en page: 40-55 title: A Tutorial on Fisher information type: article-journal URL: http://arxiv.org/abs/1705.01064 volume: '80' - id: MartensDeep2010 accessed: - year: 2018 month: 4 day: 2 author: - family: Martens given: James citation-key: MartensDeep2010 collection-title: ICML'10 container-title: >- Proceedings of the 27th International Conference on International Conference on Machine Learning event-place: USA ISBN: 978-1-60558-907-7 issued: - year: 2010 page: 735–742 publisher: Omnipress publisher-place: USA title: Deep Learning via Hessian-free Optimization type: paper-conference URL: http://www.cs.utoronto.ca/~jmartens/docs/Deep_HessianFree.pdf - id: MartensLearning2011 accessed: - year: 2018 month: 4 day: 2 author: - family: Martens given: James - family: Sutskever given: Ilya citation-key: MartensLearning2011 collection-title: ICML'11 container-title: >- Proceedings of the 28th International Conference on International Conference on Machine Learning event-place: USA ISBN: 978-1-4503-0619-5 issued: - year: 2011 page: 1033–1040 publisher: Omnipress publisher-place: USA title: Learning Recurrent Neural Networks with Hessian-free Optimization type: paper-conference URL: http://dl.acm.org/citation.cfm?id=3104482.3104612 - id: MartensNew2020 accessed: - year: 2020 month: 9 day: 17 author: - family: Martens given: James citation-key: MartensNew2020 container-title: Journal of Machine Learning Research ISSN: 1533-7928 issue: '146' issued: - year: 2020 page: 1-76 title: New Insights and Perspectives on the Natural Gradient Method type: article-journal URL: http://jmlr.org/papers/v21/17-678.html volume: '21' - id: MartensOptimizing2015 accessed: - year: 2022 month: 1 day: 6 author: - family: Martens given: James - family: Grosse given: Roger citation-key: MartensOptimizing2015 container-title: Proceedings of the 32nd International Conference on Machine Learning event-title: International Conference on Machine Learning ISSN: 1938-7228 issued: - year: 2015 month: 6 day: 1 language: en page: 2408-2417 publisher: PMLR title: Optimizing Neural Networks with Kronecker-factored Approximate Curvature type: paper-conference URL: http://arxiv.org/abs/1503.05671 - id: MartensSECONDORDER2016 accessed: - year: 2020 month: 5 day: 26 author: - family: Martens given: James citation-key: MartensSECONDORDER2016 issued: - year: 2016 publisher: University of Toronto title: Second-Order Optimization for Neural Networks type: thesis URL: http://www.cs.toronto.edu/~jmartens/docs/thesis_phd_martens.pdf - id: MartensTraining2012 author: - family: Martens given: James - family: Sutskever given: Ilya citation-key: MartensTraining2012 collection-title: Lecture Notes in Computer Science container-title: 'Neural networks: Tricks of the trade' ISBN: 978-3-642-35288-1 978-3-642-35289-8 issued: - year: 2012 page: 479–535 publisher: Springer title: Training deep and recurrent networks with Hessian-free optimization type: chapter URL: http://www.cs.toronto.edu/~jmartens/docs/HF_book_chapter.pdf - id: MosegaardProbabilistic2002 accessed: - year: 2022 month: 1 day: 13 author: - family: Mosegaard given: Klaus - family: Tarantola given: Albert citation-key: MosegaardProbabilistic2002 container-title: International Geophysics DOI: 10.1016/S0074-6142(02)80219-4 ISBN: 978-0-12-440652-0 issued: - year: 2002 language: en page: 237-265 publisher: Elsevier title: Probabilistic approach to inverse problems type: chapter URL: https://linkinghub.elsevier.com/retrieve/pii/S0074614202802194 volume: '81' - id: NielsenElementary2018 accessed: - year: 2019 month: 12 day: 27 author: - family: Nielsen given: Frank citation-key: NielsenElementary2018 container-title: arXiv:1808.08271 [cs, math, stat] issued: - year: 2018 month: 8 day: 16 title: An elementary introduction to information geometry type: article-journal URL: http://arxiv.org/abs/1808.08271 - id: NurbekyanEfficient2022 accessed: - year: 2022 month: 7 day: 28 author: - family: Nurbekyan given: Levon - family: Lei given: Wanzhou - family: Yang given: Yunan citation-key: NurbekyanEfficient2022 DOI: 10.48550/arXiv.2202.06236 issued: - year: 2022 month: 4 day: 3 number: arXiv:2202.06236 publisher: arXiv title: >- Efficient Natural Gradient Descent Methods for Large-Scale Optimization Problems type: article URL: http://arxiv.org/abs/2202.06236 - id: OllivierOnline2017 accessed: - year: 2017 month: 7 day: 17 author: - family: Ollivier given: Yann citation-key: OllivierOnline2017 container-title: arXiv:1703.00209 [math, stat] issued: - year: 2017 month: 3 day: 1 title: Online Natural Gradient as a Kalman Filter type: article-journal URL: http://arxiv.org/abs/1703.00209 - id: OsawaASDL2023 accessed: - year: 2023 month: 6 day: 2 author: - family: Osawa given: Kazuki - family: Ishikawa given: Satoki - family: Yokota given: Rio - family: Li given: Shigang - family: Hoefler given: Torsten citation-key: OsawaASDL2023 issued: - year: 2023 month: 5 day: 8 language: en number: arXiv:2305.04684 publisher: arXiv title: 'ASDL: A Unified Interface for Gradient Preconditioning in PyTorch' type: article URL: http://arxiv.org/abs/2305.04684 - id: PavlovInterior2020 accessed: - year: 2021 month: 12 day: 8 author: - family: Pavlov given: Andrei - family: Shames given: Iman - family: Manzie given: Chris citation-key: PavlovInterior2020 container-title: arXiv:2004.12710 [cs, eess, math] issued: - year: 2020 month: 10 day: 20 language: en title: Interior Point Differential Dynamic Programming type: article-journal URL: http://arxiv.org/abs/2004.12710 - id: RobbinsConvergence1971 accessed: - year: 2018 month: 6 day: 13 author: - family: Robbins given: H. - family: Siegmund given: D. citation-key: RobbinsConvergence1971 container-title: Optimizing Methods in Statistics DOI: 10.1016/B978-0-12-604550-5.50015-8 editor: - family: Rustagi given: Jagdish S. ISBN: 978-0-12-604550-5 issued: - year: 1971 page: 233-257 publisher: Academic Press title: >- A convergence theorem for non negative almost supermartingales and some applications type: chapter URL: https://www.sciencedirect.com/science/article/pii/B9780126045505500158 - id: RuppertNewtonRaphson1985 author: - family: Ruppert given: David citation-key: RuppertNewtonRaphson1985 container-title: The Annals of Statistics container-title-short: The Annals of Statistics DOI: 10.1214/aos/1176346589 ISSN: 0090-5364, 2168-8966 issue: '1' issued: - year: 1985 page: 236-245 title: A Newton-Raphson Version of the Multivariate Robbins-Monro Procedure type: article-journal volume: '13' - id: SalimbeniNatural2018 accessed: - year: 2020 month: 5 day: 26 author: - family: Salimbeni given: Hugh - family: Eleftheriadis given: Stefanos - family: Hensman given: James citation-key: SalimbeniNatural2018 container-title: International Conference on Artificial Intelligence and Statistics event-title: International Conference on Artificial Intelligence and Statistics ISSN: 1938-7228 issued: - year: 2018 month: 3 day: 31 language: en page: 689-697 section: Machine Learning title: >- Natural Gradients in Practice: Non-Conjugate Variational Inference in Gaussian Process Models type: paper-conference URL: http://arxiv.org/abs/1803.09151 - id: SchraudolphFast2002 accessed: - year: 2018 month: 4 day: 2 author: - family: Schraudolph given: Nicol N. citation-key: SchraudolphFast2002 container-title: Neural Computation container-title-short: Neural Computation DOI: 10.1162/08997660260028683 ISSN: 0899-7667 issue: '7' issued: - year: 2002 month: 7 day: 1 page: 1723-1738 title: Fast Curvature Matrix-Vector Products for Second-Order Gradient Descent type: article-journal URL: https://nic.schraudolph.org/pubs/Schraudolph02.pdf volume: '14' - id: SchraudolphStochastic2007 accessed: - year: 2020 month: 1 day: 22 author: - family: Schraudolph given: Nicol N. - family: Yu given: Jin - family: Günter given: Simon citation-key: SchraudolphStochastic2007 container-title: Artificial Intelligence and Statistics event-title: Artificial Intelligence and Statistics issued: - year: 2007 month: 3 day: 11 language: en page: 436-443 title: A Stochastic Quasi-Newton Method for Online Convex Optimization type: paper-conference URL: http://proceedings.mlr.press/v2/schraudolph07a.html - id: WilkinsonBayesNewton2021 accessed: - year: 2022 month: 7 day: 28 author: - family: Wilkinson given: William J. - family: Särkkä given: Simo - family: Solin given: Arno citation-key: WilkinsonBayesNewton2021 DOI: 10.48550/arXiv.2111.01721 issued: - year: 2021 month: 11 day: 3 number: arXiv:2111.01721 publisher: arXiv title: Bayes-Newton Methods for Approximate Bayesian Inference with PSD Guarantees type: article URL: http://arxiv.org/abs/2111.01721 - id: YaoPyHessian2020 accessed: - year: 2021 month: 8 day: 5 author: - family: Yao given: Zhewei - family: Gholami given: Amir - family: Keutzer given: Kurt - family: Mahoney given: Michael citation-key: YaoPyHessian2020 container-title: arXiv:1912.07145 [cs, math] issued: - year: 2020 month: 3 day: 5 title: 'PyHessian: Neural Networks Through the Lens of the Hessian' type: paper-conference URL: http://arxiv.org/abs/1912.07145 - id: YurtseverScalable2021 accessed: - year: 2023 month: 4 day: 21 author: - family: Yurtsever given: Alp - family: Tropp given: Joel A. - family: Fercoq given: Olivier - family: Udell given: Madeleine - family: Cevher given: Volkan citation-key: YurtseverScalable2021 container-title: SIAM Journal on Mathematics of Data Science DOI: 10.1137/19M1305045 issue: '1' issued: - year: 2021 month: 1 page: 171-200 publisher: Society for Industrial and Applied Mathematics title: Scalable Semidefinite Programming type: article-journal URL: https://arxiv.org/abs/1912.02949v2 volume: '3' - id: ZellnerOptimal1988 accessed: - year: 2020 month: 9 day: 7 author: - family: Zellner given: Arnold citation-key: ZellnerOptimal1988 container-title: The American Statistician DOI: 10.1080/00031305.1988.10475585 ISSN: 0003-1305 issue: '4' issued: - year: 1988 month: 11 day: 1 page: 278-280 publisher: Taylor & Francis title: Optimal Information Processing and Bayes's Theorem type: article-journal URL: https://ageconsearch.umn.edu/record/296078/files/usc043.pdf volume: '42' - id: ZhangNoisy2018 accessed: - year: 2023 month: 8 day: 28 author: - family: Zhang given: Guodong - family: Sun given: Shengyang - family: Duvenaud given: David - family: Grosse given: Roger citation-key: ZhangNoisy2018 container-title: Proceedings of the 35th International Conference on Machine Learning event-title: International Conference on Machine Learning ISSN: 2640-3498 issued: - year: 2018 month: 7 day: 3 language: en page: 5852-5861 publisher: PMLR title: Noisy Natural Gradient as Variational Inference type: paper-conference URL: http://arxiv.org/abs/1712.02390 ...