Gaussian Process Behaviour in Wide Deep Neural Networks

30 April 2018

Papers citing "Gaussian Process Behaviour in Wide Deep Neural Networks"

50 / 391 papers shown

Title
On the (Non-)Robustness of Two-Layer Neural Networks in Different Learning Regimes Elvis Dohmatob A. Bietti AAML 39 13 0 22 Mar 2022
A Framework and Benchmark for Deep Batch Active Learning for Regression David Holzmüller Viktor Zaverkin Johannes Kastner Ingo Steinwart UQCV BDL GP 26 34 0 17 Mar 2022
On Connecting Deep Trigonometric Networks with Deep Gaussian Processes: Covariance, Expressivity, and Neural Tangent Kernel Chi-Ken Lu Patrick Shafto BDL 34 0 0 14 Mar 2022
Quantitative Gaussian Approximation of Randomly Initialized Deep Neural Networks Andrea Basteri Dario Trevisan BDL 24 20 0 14 Mar 2022
Deep Regression Ensembles Antoine Didisheim Bryan Kelly Semyon Malamud UQCV 17 4 0 10 Mar 2022
Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer Greg Yang J. E. Hu Igor Babuschkin Szymon Sidor Xiaodong Liu David Farhi Nick Ryder J. Pachocki Weizhu Chen Jianfeng Gao 26 149 0 07 Mar 2022
Generalization Through The Lens Of Leave-One-Out Error Gregor Bachmann Thomas Hofmann Aurelien Lucchi 67 7 0 07 Mar 2022
Contrasting random and learned features in deep Bayesian linear regression Jacob A. Zavatone-Veth William L. Tong Cengiz Pehlevan BDL MLT 28 27 0 01 Mar 2022
Wide Mean-Field Bayesian Neural Networks Ignore the Data Beau Coker W. Bruinsma David R. Burt Weiwei Pan Finale Doshi-Velez UQCV BDL 44 22 0 23 Feb 2022
A duality connecting neural network and cosmological dynamics Sven Krippendorf M. Spannowsky AI4CE 30 8 0 22 Feb 2022
UncertaINR: Uncertainty Quantification of End-to-End Implicit Neural Representations for Computed Tomography Francisca Vasconcelos Bobby He Nalini Singh Yee Whye Teh BDL OOD UQCV 37 12 0 22 Feb 2022
Learning from Randomly Initialized Neural Network Features Ehsan Amid Rohan Anil W. Kotłowski Manfred K. Warmuth MLT 24 14 0 13 Feb 2022
Lossy Gradient Compression: How Much Accuracy Can One Bit Buy? Sadaf Salehkalaibar Stefano Rini FedML 35 4 0 06 Feb 2022
Learning Representation from Neural Fisher Kernel with Low-rank Approximation Ruixiang Zhang Shuangfei Zhai Etai Littwin J. Susskind SSL 36 3 0 04 Feb 2022
Deep Layer-wise Networks Have Closed-Form Weights Chieh-Tsai Wu A. Masoomi Arthur Gretton Jennifer Dy 29 3 0 01 Feb 2022
Neural Tangent Kernel Beyond the Infinite-Width Limit: Effects of Depth and Initialization Mariia Seleznova Gitta Kutyniok 179 16 0 01 Feb 2022
Stochastic Neural Networks with Infinite Width are Deterministic Liu Ziyin Hanlin Zhang Xiangming Meng Yuting Lu Eric P. Xing Masakuni Ueda 34 3 0 30 Jan 2022
Kernel Methods and Multi-layer Perceptrons Learn Linear Models in High Dimensions Mojtaba Sahraee-Ardakan M. Emami Parthe Pandit S. Rangan A. Fletcher 41 9 0 20 Jan 2022
Deep convolutional neural network for shape optimization using level-set approach Wrik Mallik N. Farvolden J. Jelovica R. Jaiman 11 3 0 17 Jan 2022
On neural network kernels and the storage capacity problem Jacob A. Zavatone-Veth Cengiz Pehlevan 6 6 0 12 Jan 2022
Eigenvalue Distribution of Large Random Matrices Arising in Deep Neural Networks: Orthogonal Case L. Pastur 19 5 0 12 Jan 2022
Separation of Scales and a Thermodynamic Description of Feature Learning in Some CNNs Inbar Seroussi Gadi Naveh Zohar Ringel 35 51 0 31 Dec 2021
Bayesian neural network priors for edge-preserving inversion Chen Li Matthew M. Dunlop G. Stadler 20 12 0 20 Dec 2021
GPEX, A Framework For Interpreting Artificial Neural Networks Amir Akbarnejad G. Bigras Nilanjan Ray 47 4 0 18 Dec 2021
Posterior contraction rates for constrained deep Gaussian processes in density estimation and classication François Bachoc A. Lagnoux 26 4 0 14 Dec 2021
Eigenspace Restructuring: a Principle of Space and Frequency in Neural Networks Lechao Xiao 34 22 0 10 Dec 2021
Infinite Neural Network Quantum States: Entanglement and Training Dynamics Di Luo James Halverson 25 6 0 01 Dec 2021
Dependence between Bayesian neural network units M. Vladimirova Julyan Arbel Stéphane Girard BDL 28 3 0 29 Nov 2021
Critical Initialization of Wide and Deep Neural Networks through Partial Jacobians: General Theory and Applications Darshil Doshi Tianyu He Andrey Gromov 30 8 0 23 Nov 2021
Depth induces scale-averaging in overparameterized linear Bayesian neural networks Jacob A. Zavatone-Veth Cengiz Pehlevan BDL UQCV MDE 41 9 0 23 Nov 2021
On the Equivalence between Neural Network and Support Vector Machine Yilan Chen Wei Huang Lam M. Nguyen Tsui-Wei Weng AAML 25 18 0 11 Nov 2021
Periodic Activation Functions Induce Stationarity Lassi Meronen Martin Trapp Arno Solin BDL 22 20 0 26 Oct 2021
Learning curves for Gaussian process regression with power-law priors and targets Hui Jin P. Banerjee Guido Montúfar 14 17 0 23 Oct 2021
Feature Learning and Signal Propagation in Deep Neural Networks Yizhang Lou Chris Mingard Yoonsoo Nam Soufiane Hayou MDE 29 17 0 22 Oct 2021
On out-of-distribution detection with Bayesian neural networks Francesco DÁngelo Christian Henning BDL UQCV 26 6 0 12 Oct 2021
Kernel Interpolation as a Bayes Point Machine Jeremy Bernstein Alexander R. Farhang Yisong Yue BDL 32 4 0 08 Oct 2021
Bayesian neural network unit priors and generalized Weibull-tail property M. Vladimirova Julyan Arbel Stéphane Girard BDL 54 9 0 06 Oct 2021
On the Impact of Stable Ranks in Deep Nets B. Georgiev L. Franken Mayukh Mukherjee Georgios Arvanitidis 21 3 0 05 Oct 2021
Random matrices in service of ML footprint: ternary random features with no performance loss Hafiz Tiomoko Ali Zhenyu Liao Romain Couillet 44 7 0 05 Oct 2021
Deformed semicircle law and concentration of nonlinear random matrices for ultra-wide neural networks Zhichao Wang Yizhe Zhu 37 18 0 20 Sep 2021
Uniform Generalization Bounds for Overparameterized Neural Networks Sattar Vakili Michael Bromberg Jezabel R. Garcia Da-shan Shiu A. Bernacchia 25 19 0 13 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 32 10 0 30 Aug 2021
Nonperturbative renormalization for the neural network-QFT correspondence Harold Erbin Vincent Lahoche D. O. Samary 41 30 0 03 Aug 2021
Deep Stable neural networks: large-width asymptotics and convergence rates Stefano Favaro S. Fortini Stefano Peluchetti BDL 30 14 0 02 Aug 2021
Dataset Distillation with Infinitely Wide Convolutional Networks Timothy Nguyen Roman Novak Lechao Xiao Jaehoon Lee DD 51 231 0 27 Jul 2021
A variational approximate posterior for the deep Wishart process Sebastian W. Ober Laurence Aitchison BDL 24 11 0 21 Jul 2021
Epistemic Neural Networks Ian Osband Zheng Wen M. Asghari Vikranth Dwaracherla M. Ibrahimi Xiyuan Lu Benjamin Van Roy UQCV BDL 30 98 0 19 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
Logit-based Uncertainty Measure in Classification Huiyue Wu Diego Klabjan EDL BDL UQCV 20 6 0 06 Jul 2021
Random Neural Networks in the Infinite Width Limit as Gaussian Processes Boris Hanin BDL 32 44 0 04 Jul 2021