Papers
Topics
Authors
Recent
Search
2000 character limit reached

Quantitative Gaussian Approximation of Randomly Initialized Deep Neural Networks

Published 14 Mar 2022 in cs.LG, math.PR, and stat.ML | (2203.07379v2)

Abstract: Given any deep fully connected neural network, initialized with random Gaussian parameters, we bound from above the quadratic Wasserstein distance between its output distribution and a suitable Gaussian process. Our explicit inequalities indicate how the hidden and output layers sizes affect the Gaussian behaviour of the network and quantitatively recover the distributional convergence results in the wide limit, i.e., if all the hidden layers sizes become large.

Authors (2)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (39)
  1. Luigi Ambrosio, Nicola Gigli and Giuseppe Savaré “Metric measure spaces with Riemannian Ricci curvature bounded from below” In Duke Mathematical Journal 163.7 Duke University Press, 2014, pp. 1405–1490
  2. Devanshu Agrawal, Theodore Papamarkou and Jacob Hinkle “Wide Neural Networks with Bottlenecks are Deep Gaussian Processes” In Journal of Machine Learning Research 21.175, 2020, pp. 1–66 URL: http://jmlr.org/papers/v21/20-017.html
  3. Thomas Bonis “Stein’s method for normal approximation in Wasserstein distances with application to the multivariate central limit theorem” In Probab. Theory Relat. Fields 178.3, 2020, pp. 827–860 DOI: 10.1007/s00440-020-00989-4
  4. Anastasia Borovykh “A Gaussian Process perspective on Convolutional Neural Networks” arXiv: 1810.10798 In arXiv:1810.10798 [cs, stat], 2019 URL: http://arxiv.org/abs/1810.10798
  5. “Large-width functional asymptotics for deep Gaussian neural networks”, 2020 URL: https://openreview.net/forum?id=0aW6lYOYB7d
  6. “A review on neural networks with random weights” In Neurocomputing 275 Elsevier, 2018, pp. 278–287
  7. Mark K. Cowan “battlesnake/neural” original-date: 2013-08-12T23:46:47Z, 2022 URL: https://github.com/battlesnake/neural
  8. “Kernel methods for deep learning” In Advances in neural information processing systems 22, 2009
  9. Ronen Eldan, Dan Mikulincer and Tselil Schramm “Non-asymptotic approximations of neural networks by Gaussian processes” In Conference on Learning Theory, 2021, pp. 1754–1775 PMLR
  10. “On the rate of convergence in Wasserstein distance of the empirical measure” In Probability theory and related fields 162.3-4 Springer, 2015, pp. 707–738
  11. “Pot: Python optimal transport” In The Journal of Machine Learning Research 22.1 JMLRORG, 2021, pp. 3571–3578
  12. Ian Goodfellow, Yoshua Bengio and Aaron Courville “Deep Learning” http://www.deeplearningbook.org MIT Press, 2016
  13. “Generative Adversarial Nets” In Advances in Neural Information Processing Systems 27 Curran Associates, Inc., 2014 URL: https://proceedings.neurips.cc/paper/2014/hash/5ca3e9b122f61f8f06494c97b1afccf3-Abstract.html
  14. Adrià Garriga-Alonso, Carl Edward Rasmussen and Laurence Aitchison “Deep Convolutional Networks as shallow Gaussian Processes”, 2018 URL: https://openreview.net/forum?id=Bklfsi0cKm
  15. J Leo Hemmen and Tsuneya Ando “An inequality for trace ideals” In Communications in Mathematical Physics 76.2 Springer, 1980, pp. 143–148
  16. Boris Hanin “Random Neural Networks in the Infinite Width Limit as Gaussian Processes” arXiv: 2107.01562 In arXiv:2107.01562 [cs, math, stat], 2021 URL: http://arxiv.org/abs/2107.01562
  17. “Exact posterior distributions of wide Bayesian neural networks”, 2020 URL: https://openreview.net/forum?id=s279nFs8NNT
  18. Adam Klukowski “Rate of Convergence of Polynomial Networks to Gaussian Processes” In Conference on Learning Theory, 2022, pp. 701–722 PMLR
  19. Yann LeCun, Yoshua Bengio and Geoffrey Hinton “Deep learning” Number: 7553 Publisher: Nature Publishing Group In Nature 521.7553, 2015, pp. 436–444 DOI: 10.1038/nature14539
  20. “Deep Neural Networks as Gaussian Processes”, 2018 URL: https://openreview.net/forum?id=B1EA-M-0Z
  21. “Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent” In Advances in Neural Information Processing Systems 32 Curran Associates, Inc., 2019 URL: https://proceedings.neurips.cc/paper/2019/hash/0d1a9651497a38d8b1c3871c84528bd4-Abstract.html
  22. “Gaussian Process Behaviour in Wide Deep Neural Networks”, 2018 URL: https://openreview.net/forum?id=H1-nGgWC-
  23. Song Mei, Andrea Montanari and Phan-Minh Nguyen “A mean field view of the landscape of two-layer neural networks” In Proceedings of the National Academy of Sciences 115.33, 2018, pp. E7665–E7671 DOI: 10.1073/pnas.1806579115
  24. Takuo Matsubara, Chris.J. Oates and F. Briol “The Ridgelet Prior: A Covariance Function Approach to Prior Specification for Bayesian Neural Networks” In J. Mach. Learn. Res. 22, 2020, pp. 157:1–157:57 URL: https://api.semanticscholar.org/CorpusID:223956904
  25. Meenal V Narkhede, Prashant P Bartakke and Mukul S Sutaone “A review on weight initialization strategies for neural networks” In Artificial intelligence review 55.1 Springer, 2022, pp. 291–322
  26. Radford M. Neal “Priors for Infinite Networks” In Bayesian Learning for Neural Networks, Lecture Notes in Statistics New York, NY: Springer, 1996, pp. 29–53 DOI: 10.1007/978-1-4612-0745-0˙2
  27. “Neural Tangents: Fast and Easy Infinite Neural Networks in Python” In International Conference on Learning Representations, 2020 URL: https://github.com/google/neural-tangents
  28. Phan-Minh Nguyen and Huy Tuan Pham “A Rigorous Framework for the Mean Field Limit of Multilayer Neural Networks” arXiv: 2001.11443 In arXiv:2001.11443 [cond-mat, stat], 2021 URL: http://arxiv.org/abs/2001.11443
  29. “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
  30. Stefano Peluchetti, Stefano Favaro and Sandra Fortini “Stable behaviour of infinitely wide deep neural networks” ISSN: 2640-3498 In Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics PMLR, 2020, pp. 1137–1146 URL: https://proceedings.mlr.press/v108/peluchetti20b.html
  31. Frank Rosenblatt “The perceptron: a probabilistic model for information storage and organization in the brain.” In Psychological review 65.6 American Psychological Association, 1958, pp. 386
  32. Daniel A Roberts, Sho Yaida and Boris Hanin “The principles of deep learning theory” Cambridge University Press Cambridge, MA, USA, 2022
  33. Filippo Santambrogio “Optimal transport for applied mathematicians” In Birkäuser, NY 55.58-63 Springer, 2015, pp. 94
  34. Terrence J. Sejnowski “The Deep Learning Revolution” Google-Books-ID: 9xZxDwAAQBAJ MIT Press, 2018
  35. Cédric Villani “Optimal transport: old and new” Springer, 2009
  36. CK Williams and Carl Edward Rasmussen “Gaussian processes for machine learning, vol. 2, no. 3” Cambridge, MA, USA: MIT Press, 2006
  37. Greg Yang “Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes” In Advances in Neural Information Processing Systems 32 Curran Associates, Inc., 2019 URL: https://proceedings.neurips.cc/paper/2019/hash/5e69fda38cda2060819766569fd93aa5-Abstract.html
  38. Greg Yang “Wide feedforward or recurrent neural networks of any architecture are gaussian processes” In Advances in Neural Information Processing Systems 32, 2019
  39. “Tensor programs iib: Architectural universality of neural tangent kernel training dynamics” In International Conference on Machine Learning, 2021, pp. 11762–11772 PMLR
Citations (16)

Summary

No one has generated a summary of this paper yet.

Paper to Video (Beta)

No one has generated a video about this paper yet.

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.

Collections

Sign up for free to add this paper to one or more collections.