Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes

11 October 2018

Jascha Narain Sohl-Dickstein

UQCV

BDL

ArXiv PDF HTML

Papers citing "Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes"

50 / 228 papers shown

Title
Deep Stable neural networks: large-width asymptotics and convergence rates Stefano Favaro S. Fortini Stefano Peluchetti BDL 28 14 0 02 Aug 2021
Deep Networks Provably Classify Data on Curves Tingran Wang Sam Buchanan D. Gilboa John N. Wright 23 9 0 29 Jul 2021
Dataset Distillation with Infinitely Wide Convolutional Networks Timothy Nguyen Roman Novak Lechao Xiao Jaehoon Lee DD 35 229 0 27 Jul 2021
A variational approximate posterior for the deep Wishart process Sebastian W. Ober Laurence Aitchison BDL 17 11 0 21 Jul 2021
Understanding the Distributions of Aggregation Layers in Deep Neural Networks Eng-Jon Ong S. Husain M. Bober FAtt FedML AI4CE 11 2 0 09 Jul 2021
Random Neural Networks in the Infinite Width Limit as Gaussian Processes Boris Hanin BDL 24 43 0 04 Jul 2021
Scale Mixtures of Neural Network Gaussian Processes Hyungi Lee Eunggu Yun Hongseok Yang Juho Lee UQCV BDL 13 7 0 03 Jul 2021
Subspace Clustering Based Analysis of Neural Networks Uday Singh Saini Pravallika Devineni Evangelos E. Papalexakis GNN 14 1 0 02 Jul 2021
Implicit Acceleration and Feature Learning in Infinitely Wide Neural Networks with Bottlenecks Etai Littwin Omid Saremi Shuangfei Zhai Vimal Thilak Hanlin Goh J. Susskind Greg Yang 25 3 0 01 Jul 2021
$α$ -Stable convergence of heavy-tailed infinitely-wide neural networks Paul Jung Hoileong Lee Jiho Lee Hongseok Yang 8 5 0 18 Jun 2021
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation Haoxiang Wang Han Zhao Bo-wen Li 37 88 0 16 Jun 2021
Locality defeats the curse of dimensionality in convolutional teacher-student scenarios Alessandro Favero Francesco Cagnetta M. Wyart 27 31 0 16 Jun 2021
How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspective Akhilan Boopathy Ila Fiete 16 9 0 15 Jun 2021
Scaling Neural Tangent Kernels via Sketching and Random Features A. Zandieh Insu Han H. Avron N. Shoham Chaewon Kim Jinwoo Shin 11 31 0 15 Jun 2021
Precise characterization of the prior predictive distribution of deep ReLU networks Lorenzo Noci Gregor Bachmann Kevin Roth Sebastian Nowozin Thomas Hofmann BDL UQCV 21 32 0 11 Jun 2021
The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective Geoff Pleiss John P. Cunningham 28 24 0 11 Jun 2021
A self consistent theory of Gaussian Processes captures feature learning effects in finite CNNs Gadi Naveh Z. Ringel SSL MLT 30 31 0 08 Jun 2021
The Future is Log-Gaussian: ResNets and Their Infinite-Depth-and-Width Limit at Initialization Mufan Bill Li Mihai Nica Daniel M. Roy 28 33 0 07 Jun 2021
Reverse Engineering the Neural Tangent Kernel James B. Simon Sajant Anand M. DeWeese 27 9 0 06 Jun 2021
Asymptotics of representation learning in finite Bayesian neural networks Jacob A. Zavatone-Veth Abdulkadir Canatar Benjamin S. Ruben C. Pehlevan 21 31 0 01 Jun 2021
Priors in Bayesian Deep Learning: A Review Vincent Fortuin UQCV BDL 29 124 0 14 May 2021
Deep Neural Networks as Point Estimates for Deep Gaussian Processes Vincent Dutordoir J. Hensman Mark van der Wilk Carl Henrik Ek Zoubin Ghahramani N. Durrande BDL UQCV 10 30 0 10 May 2021
Tensor Programs IIb: Architectural Universality of Neural Tangent Kernel Training Dynamics Greg Yang Etai Littwin 9 64 0 08 May 2021
ResMLP: Feedforward networks for image classification with data-efficient training Hugo Touvron Piotr Bojanowski Mathilde Caron Matthieu Cord Alaaeldin El-Nouby ... Gautier Izacard Armand Joulin Gabriel Synnaeve Jakob Verbeek Hervé Jégou VLM 21 655 0 07 May 2021
What Are Bayesian Neural Network Posteriors Really Like? Pavel Izmailov Sharad Vikram Matthew D. Hoffman A. Wilson UQCV BDL 17 366 0 29 Apr 2021
On the validity of kernel approximations for orthogonally-initialized neural networks James Martens 8 3 0 13 Apr 2021
How rotational invariance of common kernels prevents generalization in high dimensions Konstantin Donhauser Mingqi Wu Fanny Yang 15 22 0 09 Apr 2021
Learning with Neural Tangent Kernels in Near Input Sparsity Time A. Zandieh 4 0 0 01 Apr 2021
A Temporal Kernel Approach for Deep Learning with Continuous-time Information Da Xu Chuanwei Ruan Evren Körpeoglu Sushant Kumar Kannan Achan SyDa AI4TS 14 4 0 28 Mar 2021
Weighted Neural Tangent Kernel: A Generalized and Improved Network-Induced Kernel Lei Tan Shutong Wu Xiaolin Huang 21 1 0 22 Mar 2021
Why flatness does and does not correlate with generalization for deep neural networks Shuo Zhang Isaac Reid Guillermo Valle Pérez A. Louis 11 8 0 10 Mar 2021
Approximation and Learning with Deep Convolutional Models: a Kernel Perspective A. Bietti 29 29 0 19 Feb 2021
Quantum field-theoretic machine learning Dimitrios Bachtis Gert Aarts B. Lucini AI4CE 19 28 0 18 Feb 2021
Non-asymptotic approximations of neural networks by Gaussian processes Ronen Eldan Dan Mikulincer T. Schramm 33 24 0 17 Feb 2021
Double-descent curves in neural networks: a new perspective using Gaussian processes Ouns El Harzli Bernardo Cuenca Grau Guillermo Valle Pérez A. Louis 15 6 0 14 Feb 2021
Explaining Neural Scaling Laws Yasaman Bahri Ethan Dyer Jared Kaplan Jaehoon Lee Utkarsh Sharma 27 250 0 12 Feb 2021
Bayesian Neural Network Priors Revisited Vincent Fortuin Adrià Garriga-Alonso Sebastian W. Ober F. Wenzel Gunnar Rätsch Richard E. Turner Mark van der Wilk Laurence Aitchison BDL UQCV 64 137 0 12 Feb 2021
Meta-Learning with Neural Tangent Kernels Yufan Zhou Zhenyi Wang Jiayi Xian Changyou Chen Jinhui Xu 14 20 0 07 Feb 2021
Faster Kernel Interpolation for Gaussian Processes Mohit Yadav Daniel Sheldon Cameron Musco BDL 13 10 0 28 Jan 2021
Implicit Bias of Linear RNNs M Motavali Emami Mojtaba Sahraee-Ardakan Parthe Pandit S. Rangan A. Fletcher 15 11 0 19 Jan 2021
Correlated Weights in Infinite Limits of Deep Convolutional Neural Networks Adrià Garriga-Alonso Mark van der Wilk 12 4 0 11 Jan 2021
Infinitely Wide Tensor Networks as Gaussian Process Erdong Guo D. Draper 14 2 0 07 Jan 2021
Perspective: A Phase Diagram for Deep Learning unifying Jamming, Feature Learning and Lazy Training Mario Geiger Leonardo Petrini M. Wyart DRL 23 11 0 30 Dec 2020
Enhanced Recurrent Neural Tangent Kernels for Non-Time-Series Data Sina Alemohammad Randall Balestriero Zichao Wang Richard Baraniuk AI4TS 11 1 0 09 Dec 2020
Analyzing Finite Neural Networks: Can We Trust Neural Tangent Kernel Theory? Mariia Seleznova Gitta Kutyniok AAML 16 29 0 08 Dec 2020
Generalization bounds for deep learning Guillermo Valle Pérez A. Louis BDL 13 44 0 07 Dec 2020
Statistical Mechanics of Deep Linear Neural Networks: The Back-Propagating Kernel Renormalization Qianyi Li H. Sompolinsky 16 69 0 07 Dec 2020
Towards NNGP-guided Neural Architecture Search Daniel S. Park Jaehoon Lee Daiyi Peng Yuan Cao Jascha Narain Sohl-Dickstein BDL 18 32 0 11 Nov 2020
Dataset Meta-Learning from Kernel Ridge-Regression Timothy Nguyen Zhourung Chen Jaehoon Lee DD 36 238 0 30 Oct 2020
Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth Thao Nguyen M. Raghu Simon Kornblith OOD 8 262 0 29 Oct 2020