Fetching the paper…
Reading the bibliography…
Bayesian neural networks are theoretically well-understood only in the infinite-width limit, where Gaussian priors over network weights yield Gaussian priors over network outputs.
Higher Transcendental Functions. Vol. I
Arthur Erdélyi, Wilhelm Magnus, Fritz Oberhettinger, and Francesco G. Tricomi · 1963
Earlier work this paper cites.
Anharmonic oscillator
Carl M Bender and Tai Tsun Wu · 1969
Earlier work this paper cites.
Tables of Integral Transforms. Vol. II
Arthur Erdélyi, Wilhelm Magnus, Fritz Oberhettinger, and Francesco G. Tricomi · 1969
Earlier work this paper cites.
Tables of Integral Transforms. Vol. I
Arthur Erdélyi, Wilhelm Magnus, Fritz Oberhettinger, and Francesco G. Tricomi · 1970
Earlier work this paper cites.
On multivariate Edgeworth expansions
Ib M Skovgaard · 1986
Earlier work this paper cites.
A practical Bayesian framework for backpropagation networks
David JC MacKay · 1992
Earlier work this paper cites.
Priors for infinite networks
Radford M Neal · 1996
Earlier work this paper cites.
Computing with infinite networks
Christopher KI Williams · 1997
Earlier work this paper cites.
A user’s guide to measure theoretic probability , volume 8
David Pollard · 2002
Earlier work this paper cites.
Exactly solved models in statistical mechanics
Rodney J Baxter · 2007
Earlier work this paper cites.
The Laplace distribution and generalizations: a revisit with applications to communications, economics, engineering, and finance
Samuel Kotz, Tomasz Kozubowski, and Krzystof Podgorski · 2012
Earlier work this paper cites.
The two-dimensional Ising model
Barry M McCoy and Tai Tsun Wu · 2014
Earlier work this paper cites.
Table of integrals, series, and products
Izrail Solomonovich Gradshteyn and Iosif Moiseevich Ryzhik · 2014
Earlier work this paper cites.
Weak commutation relations and eigenvalue statistics for products of rectangular random matrices
Jesper R. Ipsen and Mario Kieburg · 2014
Earlier work this paper cites.
Deep learning
Yann LeCun, Yoshua Bengio, and Geoffrey Hinton · 2015
Earlier work this paper cites.
Deep learning
Ian Goodfellow, Yoshua Bengio, Aaron Courville, and Yoshua Bengio · 2016
Cited alongside, same era.
Introduction to Fourier Analysis on Euclidean Spaces (PMS-32), Volume 32
Elias M Stein and Guido Weiss · 2016
Cited alongside, same era.
A correspondence between random neural networks and statistical field theory
Samuel S Schoenholz, Jeffrey Pennington, and Jascha Sohl-Dickstein · 2017
Cited alongside, same era.
Gaussian process behaviour in wide deep neural networks
Alexander G. de G. Matthews, Jiri Hron, Mark Rowland, Richard E. Turner, and Zoubin Ghahramani · 2018
Cited alongside, same era.
Deep neural networks as Gaussian processes
Jaehoon Lee, Jascha Sohl-Dickstein, Jeffrey Pennington, Roman Novak, Sam Schoenholz, and Yasaman Bahri · 2018
Cited alongside, same era.
Finite versus infinite neural networks: an empirical study
Jaehoon Lee, Samuel S Schoenholz, Jeffrey Pennington, Ben Adlam, Lechao Xiao, Roman Novak, and Jascha Sohl-Dickstein · 2020
Later among the works it cites.
Feature learning in infinite-width neural networks
Greg Yang and Edward J Hu · 2020
Later among the works it cites.
Wide neural networks with bottlenecks are deep gaussian processes
Devanshu Agrawal, Theodore Papamarkou, and Jacob Hinkle · 2020
Later among the works it cites.
Predicting the outputs of finite networks trained with noisy gradients
Gadi Naveh, Oded Ben-David, Haim Sompolinsky, and Zohar Ringel · 2020
Later among the works it cites.
Interpretable deep gaussian processes with moments
Chi-Ken Lu, Scott Cheng-Hsin Yang, Xiaoran Hao, and Patrick Shafto · 2020
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Greg Yang · 2019
Cited alongside, same era.
Finite size corrections for neural network Gaussian processes
Joseph M Antognini · 2019
Cited alongside, same era.
Understanding priors in Bayesian neural networks at the unit level
Mariia Vladimirova, Jakob Verbeek, Pablo Mesejo, and Julyan Arbel · 2019
Cited alongside, same era.
Why bigger is not always better: on finite and infinite neural networks
Laurence Aitchison · 2020
Cited alongside, same era.
Bayesian deep learning and a probabilistic perspective of generalization
Andrew Gordon Wilson and Pavel Izmailov · 2020
Cited alongside, same era.
Non-Gaussian processes and neural networks at finite widths
Sho Yaida · 2020
Cited alongside, same era.
Asymptotics of wide networks from Feynman diagrams
Ethan Dyer and Guy Gur-Ari · 2020
Cited alongside, same era.
Later among the works it cites.
A statistical theory of cold posteriors in deep neural networks
Laurence Aitchison · 2021
Closest in time.
Neural networks and quantum field theory
James Halverson, Anindita Maiti, and Keegan Stoner · 2021
Closest in time.
Bayesian neural network priors revisited
Vincent Fortuin, Adrià Garriga-Alonso, Florian Wenzel, Gunnar Rätsch, Richard Turner, Mark van der Wilk, and Laurence Aitchison · 2021
Closest in time.
What are bayesian neural network posteriors really like?
Pavel Izmailov, Sharad Vikram, Matthew D Hoffman, and Andrew Gordon Gordon Wilson · 2021
Closest in time.
NIST Digital Library of Mathematical Functions
DLMF · 2021
Closest in time.
The limitations of large width in neural networks: A deep Gaussian process perspective
Geoff Pleiss and John P Cunningham · 2021
Closest in time.
Precise characterization of the prior predictive distribution of deep ReLU networks
Lorenzo Noci, Gregor Bachmann, Kevin Roth, Sebastian Nowozin, and Thomas Hofmann · 2021
Closest in time.
Random neural networks in the infinite width limit as Gaussian processes
Boris Hanin · 2021
Closest in time.
Non-asymptotic results for singular values of Gaussian matrix products
Boris Hanin and Grigoris Paouris · 2021
Closest in time.