The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective

11 June 2021

Papers citing "The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective"

19 / 19 papers shown

Title
Theoretical Limitations of Ensembles in the Age of Overparameterization Niclas Dern John P. Cunningham Geoff Pleiss BDL UQCV 29 0 0 21 Oct 2024
A Unified Kernel for Neural Network Learning Shao-Qun Zhang Zong-Yi Chen Yong-Ming Tian Xun Lu 29 1 0 26 Mar 2024
On permutation symmetries in Bayesian neural network posteriors: a variational perspective Simone Rossi Ankit Singh T. Hannagan 24 2 0 16 Oct 2023
On the Disconnect Between Theory and Practice of Neural Networks: Limits of the NTK Perspective Jonathan Wenger Felix Dangel Agustinus Kristiadi 25 0 0 29 Sep 2023
Convolutional Deep Kernel Machines Edward Milsom Ben Anson Laurence Aitchison BDL 18 5 0 18 Sep 2023
Bayesian inference with finitely wide neural networks Chi-Ken Lu BDL 24 0 0 06 Mar 2023
Gaussian Process-Gated Hierarchical Mixtures of Experts Yuhao Liu Marzieh Ajirak P. Djuric MoE 16 1 0 09 Feb 2023
Bayesian Interpolation with Deep Linear Networks Boris Hanin Alexander Zlokapa 34 25 0 29 Dec 2022
An Empirical Analysis of the Advantages of Finite- v.s. Infinite-Width Bayesian Neural Networks Jiayu Yao Yaniv Yacoby Beau Coker Weiwei Pan Finale Doshi-Velez 19 1 0 16 Nov 2022
Variational Inference for Infinitely Deep Neural Networks Achille Nazaret David M. Blei BDL 17 11 0 21 Sep 2022
On Connecting Deep Trigonometric Networks with Deep Gaussian Processes: Covariance, Expressivity, and Neural Tangent Kernel Chi-Ken Lu Patrick Shafto BDL 26 0 0 14 Mar 2022
Complexity from Adaptive-Symmetries Breaking: Global Minima in the Statistical Mechanics of Deep Neural Networks Shaun Li AI4CE 22 0 0 03 Jan 2022
Dependence between Bayesian neural network units M. Vladimirova Julyan Arbel Stéphane Girard BDL 12 3 0 29 Nov 2021
Depth induces scale-averaging in overparameterized linear Bayesian neural networks Jacob A. Zavatone-Veth C. Pehlevan BDL UQCV MDE 36 8 0 23 Nov 2021
Conditional Deep Gaussian Processes: empirical Bayes hyperdata learning Chi-Ken Lu Patrick Shafto BDL 14 4 0 01 Oct 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 24 10 0 30 Aug 2021
Why bigger is not always better: on finite and infinite neural networks Laurence Aitchison 173 51 0 17 Oct 2019
Benefits of depth in neural networks Matus Telgarsky 123 602 0 14 Feb 2016
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning Y. Gal Zoubin Ghahramani UQCV BDL 247 9,134 0 06 Jun 2015