Deep Neural Networks as Gaussian Processes

1 November 2017

Jascha Narain Sohl-Dickstein

UQCV

BDL

ArXiv PDF HTML

Papers citing "Deep Neural Networks as Gaussian Processes"

50 / 692 papers shown

Title
Precise characterization of the prior predictive distribution of deep ReLU networks Lorenzo Noci Gregor Bachmann Kevin Roth Sebastian Nowozin Thomas Hofmann BDL UQCV 37 32 0 11 Jun 2021
The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective Geoff Pleiss John P. Cunningham 30 24 0 11 Jun 2021
Measuring the robustness of Gaussian processes to kernel choice William T. Stephenson S. Ghosh Tin D. Nguyen Mikhail Yurochkin Sameer K. Deshpande Tamara Broderick GP 27 11 0 11 Jun 2021
Learning effective stochastic differential equations from microscopic simulations: linking stochastic numerics to deep learning Felix Dietrich Alexei Makeev George A. Kevrekidis N. Evangelou Tom S. Bertalan Sebastian Reich Ioannis G. Kevrekidis DiffM 39 38 0 10 Jun 2021
A Neural Tangent Kernel Perspective of GANs Jean-Yves Franceschi Emmanuel de Bézenac Ibrahim Ayed Mickaël Chen Sylvain Lamprier Patrick Gallinari 39 26 0 10 Jun 2021
Ghosts in Neural Networks: Existence, Structure and Role of Infinite-Dimensional Null Space Sho Sonoda Isao Ishikawa Masahiro Ikeda BDL 24 9 0 09 Jun 2021
A self consistent theory of Gaussian Processes captures feature learning effects in finite CNNs Gadi Naveh Zohar Ringel SSL MLT 41 31 0 08 Jun 2021
Learning Functional Priors and Posteriors from Data and Physics Xuhui Meng Liu Yang Zhiping Mao J. Ferrandis George Karniadakis AI4CE 35 61 0 08 Jun 2021
The Future is Log-Gaussian: ResNets and Their Infinite-Depth-and-Width Limit at Initialization Mufan Li Mihai Nica Daniel M. Roy 43 33 0 07 Jun 2021
Batch Normalization Orthogonalizes Representations in Deep Random Networks Hadi Daneshmand Amir Joudaki Francis R. Bach OOD 17 37 0 07 Jun 2021
Reverse Engineering the Neural Tangent Kernel James B. Simon Sajant Anand M. DeWeese 37 9 0 06 Jun 2021
Out-of-Distribution Generalization in Kernel Regression Abdulkadir Canatar Blake Bordelon Cengiz Pehlevan OODD OOD 11 13 0 04 Jun 2021
Symmetry-via-Duality: Invariant Neural Network Densities from Parameter-Space Correlators Anindita Maiti Keegan Stoner James Halverson 23 20 0 01 Jun 2021
Asymptotics of representation learning in finite Bayesian neural networks Jacob A. Zavatone-Veth Abdulkadir Canatar Benjamin S. Ruben Cengiz Pehlevan 28 28 0 01 Jun 2021
Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime Hugo Cui Bruno Loureiro Florent Krzakala Lenka Zdeborová 40 82 0 31 May 2021
Sparse Uncertainty Representation in Deep Learning with Inducing Weights H. Ritter Martin Kukla Chen Zhang Yingzhen Li UQCV BDL 63 17 0 30 May 2021
Active Learning in Bayesian Neural Networks with Balanced Entropy Learning Principle J. Woo 47 11 0 30 May 2021
Activation function design for deep networks: linearity and effective initialisation Michael Murray V. Abrol Jared Tanner ODL LLMSV 29 18 0 17 May 2021
Priors in Bayesian Deep Learning: A Review Vincent Fortuin UQCV BDL 41 124 0 14 May 2021
Sparsity-Probe: Analysis tool for Deep Learning Models Ido Ben-Shaul S. Dekel 21 4 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 18 30 0 10 May 2021
Tensor Programs IIb: Architectural Universality of Neural Tangent Kernel Training Dynamics Greg Yang Etai Littwin 22 64 0 08 May 2021
Adaptive Latent Space Tuning for Non-Stationary Distributions A. Scheinker F. Cropp S. Paiagua D. Filippetto OOD 23 3 0 08 May 2021
Uniform Convergence, Adversarial Spheres and a Simple Remedy Gregor Bachmann Seyed-Mohsen Moosavi-Dezfooli Thomas Hofmann AAML 17 8 0 07 May 2021
Uncertainty-Aware Boosted Ensembling in Multi-Modal Settings U. Sarawgi Rishab Khincha W. Zulfikar Satrajit S. Ghosh Pattie Maes UQCV 25 7 0 21 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
Artificial Neural Network Modeling for Airline Disruption Management Kolawole E. Ogunsina Wendy A. Okolo 16 5 0 05 Apr 2021
Learning with Neural Tangent Kernels in Near Input Sparsity Time A. Zandieh 14 0 0 01 Apr 2021
Initializing ReLU networks in an expressive subspace of weights Dayal Singh J. SreejithG 20 4 0 23 Mar 2021
Weighted Neural Tangent Kernel: A Generalized and Improved Network-Induced Kernel Lei Tan Shutong Wu Xiaolin Huang 26 1 0 22 Mar 2021
Data-driven Aerodynamic Analysis of Structures using Gaussian Processes I. Kavrakov A. McRobie Guido Morgenthal 13 13 0 20 Mar 2021
Why flatness does and does not correlate with generalization for deep neural networks Shuo Zhang Isaac Reid Guillermo Valle Pérez A. Louis 24 8 0 10 Mar 2021
Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective Wei Huang Yayong Li Weitao Du Jie Yin R. Xu Ling-Hao Chen Miao Zhang 31 17 0 03 Mar 2021
Computing the Information Content of Trained Neural Networks Jeremy Bernstein Yisong Yue 32 4 0 01 Mar 2021
Multi-fidelity regression using artificial neural networks: efficient approximation of parameter-dependent output quantities Mengwu Guo Andrea Manzoni Maurice Amendt Paolo Conti J. Hesthaven 85 95 0 26 Feb 2021
Neural Generalization of Multiple Kernel Learning Ahamad Navid Ghanizadeh Kamaledin Ghiasi-Shirazi R. Monsefi Mohammadreza Qaraei 13 2 0 26 Feb 2021
Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed Maria Refinetti Sebastian Goldt Florent Krzakala Lenka Zdeborová 30 72 0 23 Feb 2021
Large-width functional asymptotics for deep Gaussian neural networks Daniele Bracale Stefano Favaro S. Fortini Stefano Peluchetti 36 17 0 20 Feb 2021
Approximation and Learning with Deep Convolutional Models: a Kernel Perspective A. Bietti 36 30 0 19 Feb 2021
WGAN with an Infinitely Wide Generator Has No Spurious Stationary Points Albert No Taeho Yoon Sehyun Kwon Ernest K. Ryu GAN 27 2 0 15 Feb 2021
Cross-modal Adversarial Reprogramming Paarth Neekhara Shehzeen Samarah Hussain Jinglong Du Shlomo Dubnov F. Koushanfar Julian McAuley 27 35 0 15 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 25 6 0 14 Feb 2021
Explaining Neural Scaling Laws Yasaman Bahri Ethan Dyer Jared Kaplan Jaehoon Lee Utkarsh Sharma 32 250 0 12 Feb 2021
Bayesian Uncertainty Estimation of Learned Variational MRI Reconstruction Dominik Narnhofer Alexander Effland Erich Kobler Kerstin Hammernik Florian Knoll Thomas Pock UQCV BDL 23 49 0 12 Feb 2021
Bayesian Neural Network Priors Revisited Vincent Fortuin Adrià Garriga-Alonso Sebastian W. Ober F. Wenzel Gunnar Rätsch Richard Turner Mark van der Wilk Laurence Aitchison BDL UQCV 67 138 0 12 Feb 2021
Reducing the Amortization Gap in Variational Autoencoders: A Bayesian Random Function Approach Minyoung Kim Vladimir Pavlovic BDL 39 6 0 05 Feb 2021
Variational Bayes survival analysis for unemployment modelling P. Boškoski M. Perne M. Ramesa Biljana Mileva-Boshkoska CML 35 10 0 03 Feb 2021
A Statistician Teaches Deep Learning G. Babu David L. Banks Hyunsoo Cho David Han Hailin Sang Shouyi Wang 23 2 0 29 Jan 2021
Faster Kernel Interpolation for Gaussian Processes Mohit Yadav Daniel Sheldon Cameron Musco BDL 21 10 0 28 Jan 2021
A Similarity Measure of Gaussian Process Predictive Distributions Lucia Asencio-Martín Eduardo C. Garrido-Merchán 9 1 0 20 Jan 2021