Fetching the paper…
Reading the bibliography…
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.
“The perceptron: a probabilistic model for information storage and organization in the brain.”
Frank Rosenblatt · 1958
Earlier work this paper cites.
“An inequality for trace ideals”
J van Hemmen and Tsuneya Ando · 1980
Earlier work this paper cites.
“Priors for Infinite Networks”
Radford. Neal · 1996
Earlier work this paper cites.
“A Rigorous Framework for the Mean Field Limit of Multilayer Neural Networks” arXiv: 2001.11443
Phan-Minh Nguyen and Huy Pham · 2001
Earlier work this paper cites.
“Gaussian processes for machine learning, vol. 2, no. 3”
CK Williams and Carl Rasmussen · 2006
Earlier work this paper cites.
“Kernel methods for deep learning”
Youngmin Cho and Lawrence Saul · 2009
Earlier work this paper cites.
“Optimal transport: old and new”
Cédric Villani · 2009
Earlier work this paper cites.
“Metric measure spaces with Riemannian Ricci curvature bounded from below”
Luigi Ambrosio, Nicola Gigli and Giuseppe Savaré · 2014
Earlier work this paper cites.
“Generative Adversarial Nets”
Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville and Yoshua Bengio · 2014
Earlier work this paper cites.
“On the rate of convergence in Wasserstein distance of the empirical measure”
Nicolas Fournier and Arnaud Guillin · 2015
Earlier work this paper cites.
“Deep learning” Number: 7553 Publisher: Nature Publishing Group
Yann LeCun, Yoshua Bengio and Geoffrey Hinton · 2015
Earlier work this paper cites.
“Optimal transport for applied mathematicians”
Filippo Santambrogio · 2015
Earlier work this paper cites.
“Deep Learning” http://www.deeplearningbook.org
Ian Goodfellow, Yoshua Bengio and Aaron Courville · 2016
Earlier work this paper cites.
“A review on neural networks with random weights”
Weipeng Cao, Xizhao Wang, Zhong Ming and Jinzhu Gao · 2018
Cited alongside, same era.
“Deep Convolutional Networks as shallow Gaussian Processes”, 2018
Adrià Garriga-Alonso, Carl Rasmussen and Laurence Aitchison · 2018
Cited alongside, same era.
“Deep Neural Networks as Gaussian Processes”, 2018
Jaehoon Lee, Yasaman Bahri, Roman Novak, Samuel. Schoenholz, Jeffrey Pennington and Jascha Sohl-Dickstein · 2018
Cited alongside, same era.
“Gaussian Process Behaviour in Wide Deep Neural Networks”, 2018
Alexander.. Matthews, Jiri Hron, Mark Rowland, Richard. Turner and Zoubin Ghahramani · 2018
Cited alongside, same era.
“A mean field view of the landscape of two-layer neural networks”
Song Mei, Andrea Montanari and Phan-Minh Nguyen · 2018
Cited alongside, same era.
“The Deep Learning Revolution” Google-Books-ID: 9xZxDwAAQBAJ
Terrence. Sejnowski · 2018
“Large-width functional asymptotics for deep Gaussian neural networks”, 2020
Daniele Bracale, Stefano Favaro, Sandra Fortini and Stefano Peluchetti · 2020
Later among the works it cites.
“Exact posterior distributions of wide Bayesian neural networks”, 2020
Jiri Hron, Yasaman Bahri, Roman Novak, Jeffrey Pennington and Jascha Sohl-Dickstein · 2020
Later among the works it cites.
“The Ridgelet Prior: A Covariance Function Approach to Prior Specification for Bayesian Neural Networks”
Takuo Matsubara, Chris.. Oates and F. Briol · 2020
Later among the works it cites.
“Neural Tangents: Fast and Easy Infinite Neural Networks in Python”
Roman Novak, Lechao Xiao, Jiri Hron, Jaehoon Lee, Alexander. Alemi, Jascha Sohl-Dickstein and Samuel. Schoenholz · 2020
Later among the works it cites.
“Stable behaviour of infinitely wide deep neural networks” ISSN: 2640-3498
Stefano Peluchetti, Stefano Favaro and Sandra Fortini · 2020
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Cited alongside, same era.
“A Gaussian Process perspective on Convolutional Neural Networks” arXiv: 1810.10798
Anastasia Borovykh · 2019
Cited alongside, same era.
“Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent”
Jaehoon Lee, Lechao Xiao, Samuel Schoenholz, Yasaman Bahri, Roman Novak, Jascha Sohl-Dickstein and Jeffrey Pennington · 2019
Cited alongside, same era.
“Computational optimal transport: With applications to data science”
Gabriel Peyré and Marco Cuturi · 2019
Cited alongside, same era.
“Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes”
Greg Yang · 2019
Cited alongside, same era.
“Wide feedforward or recurrent neural networks of any architecture are gaussian processes”
Greg Yang · 2019
Cited alongside, same era.
“Wide Neural Networks with Bottlenecks are Deep Gaussian Processes”
Devanshu Agrawal, Theodore Papamarkou and Jacob Hinkle · 2020
Cited alongside, same era.
“Non-asymptotic approximations of neural networks by Gaussian processes”
Ronen Eldan, Dan Mikulincer and Tselil Schramm · 2021
Later among the works it cites.
“Pot: Python optimal transport”
Rémi Flamary, Nicolas Courty, Alexandre Gramfort, Mokhtar Alaya, Aurélie Boisbunon, Stanislas Chambon, Laetitia Chapel, Adrien Corenflos, Kilian Fatras and Nemo Fournier · 2021
Later among the works it cites.
“Random Neural Networks in the Infinite Width Limit as Gaussian Processes” arXiv: 2107.01562
Boris Hanin · 2021
Later among the works it cites.
“Tensor programs iib: Architectural universality of neural tangent kernel training dynamics”
Greg Yang and Etai Littwin · 2021
Later among the works it cites.
“battlesnake/neural” original-date: 2013-08-12T23:46:47Z, 2022
Mark. Cowan · 2022
Closest in time.
“Rate of Convergence of Polynomial Networks to Gaussian Processes”
Adam Klukowski · 2022
Closest in time.
“A review on weight initialization strategies for neural networks”
Meenal Narkhede, Prashant Bartakke and Mukul Sutaone · 2022
Closest in time.
“The principles of deep learning theory”
Daniel Roberts, Sho Yaida and Boris Hanin · 2022
Closest in time.