Disentangling Trainability and Generalization in Deep Neural Networks

30 December 2019

Papers citing "Disentangling Trainability and Generalization in Deep Neural Networks"

13 / 13 papers shown

Title
Fast Finite Width Neural Tangent Kernel Roman Novak Jascha Narain Sohl-Dickstein S. Schoenholz AAML 28 54 0 17 Jun 2022
Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis Wuyang Chen Wei Huang Xinyu Gong Boris Hanin Zhangyang Wang 38 7 0 11 May 2022
Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning Haoxiang Wang Yite Wang Ruoyu Sun Bo-wen Li 33 27 0 17 Mar 2022
Dataset Distillation with Infinitely Wide Convolutional Networks Timothy Nguyen Roman Novak Lechao Xiao Jaehoon Lee DD 51 231 0 27 Jul 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
Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective Wuyang Chen Xinyu Gong Zhangyang Wang OOD 45 232 0 23 Feb 2021
A Convergence Theory Towards Practical Over-parameterized Deep Neural Networks Asaf Noy Yi Tian Xu Y. Aflalo Lihi Zelnik-Manor Rong Jin 41 3 0 12 Jan 2021
Associative Memory in Iterated Overparameterized Sigmoid Autoencoders Yibo Jiang Cengiz Pehlevan 19 13 0 30 Jun 2020
Spectra of the Conjugate Kernel and Neural Tangent Kernel for linear-width neural networks Z. Fan Zhichao Wang 44 71 0 25 May 2020
The large learning rate phase of deep learning: the catapult mechanism Aitor Lewkowycz Yasaman Bahri Ethan Dyer Jascha Narain Sohl-Dickstein Guy Gur-Ari ODL 159 236 0 04 Mar 2020
Neural Tangents: Fast and Easy Infinite Neural Networks in Python Roman Novak Lechao Xiao Jiri Hron Jaehoon Lee Alexander A. Alemi Jascha Narain Sohl-Dickstein S. Schoenholz 38 225 0 05 Dec 2019
On the expected behaviour of noise regularised deep neural networks as Gaussian processes Arnu Pretorius Herman Kamper Steve Kroon 27 9 0 12 Oct 2019
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks Lechao Xiao Yasaman Bahri Jascha Narain Sohl-Dickstein S. Schoenholz Jeffrey Pennington 244 350 0 14 Jun 2018