Asymptotics of representation learning in finite Bayesian neural
networks

v1v2v3v4v5 (latest)

Asymptotics of representation learning in finite Bayesian neural networks

1 June 2021

Jacob A. Zavatone-Veth

Abdulkadir Canatar

Benjamin S. Ruben

Cengiz Pehlevan

ArXiv (abs)PDF HTML

Papers citing "Asymptotics of representation learning in finite Bayesian neural networks"

19 / 19 papers shown

Title
Using Autodiff to Estimate Posterior Moments, Marginals and Samples Sam Bowyer Thomas Heap Laurence Aitchison 93 1 0 26 Oct 2023
Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit Blake Bordelon Lorenzo Noci Mufan Li Boris Hanin Cengiz Pehlevan 126 27 0 28 Sep 2023
A theory of data variability in Neural Network Bayesian inference Javed Lindner David Dahmen Michael Krämer M. Helias BDL 83 3 0 31 Jul 2023
Neural Network Field Theories: Non-Gaussianity, Actions, and Locality M. Demirtaş James Halverson Anindita Maiti M. Schwartz Keegan Stoner AI4CE 75 10 0 06 Jul 2023
Structures of Neural Network Effective Theories cCaugin Ararat Tianji Cai Cem Tekin Zhengkang Zhang 117 7 0 03 May 2023
Learning curves for deep structured Gaussian feature models Jacob A. Zavatone-Veth Cengiz Pehlevan MLT 100 11 0 01 Mar 2023
Neural networks learn to magnify areas near decision boundaries Jacob A. Zavatone-Veth Sheng Yang Julian Rubinfien Cengiz Pehlevan MLT AI4CE 91 6 0 26 Jan 2023
The Curious Case of Benign Memorization Sotiris Anagnostidis Gregor Bachmann Lorenzo Noci Thomas Hofmann AAML 148 10 0 25 Oct 2022
The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization Mufan Li Mihai Nica Daniel M. Roy 107 39 0 06 Jun 2022
Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks Blake Bordelon Cengiz Pehlevan MLT 104 85 0 19 May 2022
Contrasting random and learned features in deep Bayesian linear regression Jacob A. Zavatone-Veth William L. Tong Cengiz Pehlevan BDL MLT 139 28 0 01 Mar 2022
On neural network kernels and the storage capacity problem Jacob A. Zavatone-Veth Cengiz Pehlevan 63 6 0 12 Jan 2022
Complexity from Adaptive-Symmetries Breaking: Global Minima in the Statistical Mechanics of Deep Neural Networks Shaun Li AI4CE 84 0 0 03 Jan 2022
Separation of Scales and a Thermodynamic Description of Feature Learning in Some CNNs Inbar Seroussi Gadi Naveh Zohar Ringel 113 55 0 31 Dec 2021
Depth induces scale-averaging in overparameterized linear Bayesian neural networks Jacob A. Zavatone-Veth Cengiz Pehlevan BDL UQCV MDE 106 11 0 23 Nov 2021
The edge of chaos: quantum field theory and deep neural networks Kevin T. Grosvenor R. Jefferson 90 22 0 27 Sep 2021
A theory of representation learning gives a deep generalisation of kernel methods Adam X. Yang Maxime Robeyns Edward Milsom Ben Anson Nandi Schoots Laurence Aitchison BDL 101 11 0 30 Aug 2021
The Low-Rank Simplicity Bias in Deep Networks Minyoung Huh H. Mobahi Richard Y. Zhang Brian Cheung Pulkit Agrawal Phillip Isola 131 116 0 18 Mar 2021
Neural Networks and Quantum Field Theory James Halverson Anindita Maiti Keegan Stoner 117 78 0 19 Aug 2020