How Much Over-parameterization Is Sufficient to Learn Deep ReLU Networks?

27 November 2019

Quanquan Gu

Papers citing "How Much Over-parameterization Is Sufficient to Learn Deep ReLU Networks?"

38 / 38 papers shown

Title
Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods Hossein Taheri Christos Thrampoulidis Arya Mazumdar MLT 36 0 0 13 Oct 2024
Understanding the training of infinitely deep and wide ResNets with Conditional Optimal Transport Raphael Barboni Gabriel Peyré Franccois-Xavier Vialard 37 3 0 19 Mar 2024
Fundamental Limits of Deep Learning-Based Binary Classifiers Trained with Hinge Loss T. Getu Georges Kaddoum M. Bennis 40 1 0 13 Sep 2023
Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension Moritz Haas David Holzmüller U. V. Luxburg Ingo Steinwart MLT 35 14 0 23 May 2023
Convergence beyond the over-parameterized regime using Rayleigh quotients David A. R. Robin Kevin Scaman Marc Lelarge 27 3 0 19 Jan 2023
A Functional-Space Mean-Field Theory of Partially-Trained Three-Layer Neural Networks Zhengdao Chen Eric Vanden-Eijnden Joan Bruna MLT 27 5 0 28 Oct 2022
When Expressivity Meets Trainability: Fewer than $n$ Neurons Can Work Jiawei Zhang Yushun Zhang Mingyi Hong Ruoyu Sun Zhi-Quan Luo 29 10 0 21 Oct 2022
Global Convergence of SGD On Two Layer Neural Nets Pulkit Gopalani Anirbit Mukherjee 26 5 0 20 Oct 2022
Approximation results for Gradient Descent trained Shallow Neural Networks in $1d$ R. Gentile G. Welper ODL 56 6 0 17 Sep 2022
Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization) Zhenyu Zhu Fanghui Liu Grigorios G. Chrysos V. Cevher 39 19 0 15 Sep 2022
Generalization Properties of NAS under Activation and Skip Connection Search Zhenyu Zhu Fanghui Liu Grigorios G. Chrysos V. Cevher AI4CE 28 15 0 15 Sep 2022
Informed Learning by Wide Neural Networks: Convergence, Generalization and Sampling Complexity Jianyi Yang Shaolei Ren 32 3 0 02 Jul 2022
Bounding the Width of Neural Networks via Coupled Initialization -- A Worst Case Analysis Alexander Munteanu Simon Omlor Zhao Song David P. Woodruff 33 15 0 26 Jun 2022
Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction Kaifeng Lyu Zhiyuan Li Sanjeev Arora FAtt 45 70 0 14 Jun 2022
Improved Overparametrization Bounds for Global Convergence of Stochastic Gradient Descent for Shallow Neural Networks Bartlomiej Polaczyk J. Cyranka ODL 33 3 0 28 Jan 2022
Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time Zhao Song Licheng Zhang Ruizhe Zhang 32 64 0 14 Dec 2021
Subquadratic Overparameterization for Shallow Neural Networks Chaehwan Song Ali Ramezani-Kebrya Thomas Pethick Armin Eftekhari V. Cevher 30 31 0 02 Nov 2021
Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization Difan Zou Yuan Cao Yuanzhi Li Quanquan Gu MLT AI4CE 47 38 0 25 Aug 2021
Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction Dominik Stöger Mahdi Soltanolkotabi ODL 42 75 0 28 Jun 2021
The Future is Log-Gaussian: ResNets and Their Infinite-Depth-and-Width Limit at Initialization Mufan Li Mihai Nica Daniel M. Roy 32 33 0 07 Jun 2021
Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning Zixin Wen Yuanzhi Li SSL MLT 32 131 0 31 May 2021
The Discovery of Dynamics via Linear Multistep Methods and Deep Learning: Error Estimation Q. Du Yiqi Gu Haizhao Yang Chao Zhou 26 20 0 21 Mar 2021
Experiments with Rich Regime Training for Deep Learning Xinyan Li A. Banerjee 32 2 0 26 Feb 2021
On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths Quynh N. Nguyen 45 48 0 24 Jan 2021
Reproducing Activation Function for Deep Learning Senwei Liang Liyao Lyu Chunmei Wang Haizhao Yang 36 21 0 13 Jan 2021
A Convergence Theory Towards Practical Over-parameterized Deep Neural Networks Asaf Noy Yi Tian Xu Y. Aflalo Lihi Zelnik-Manor Rong Jin 39 3 0 12 Jan 2021
Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise Spencer Frei Yuan Cao Quanquan Gu FedML MLT 64 19 0 04 Jan 2021
Neural Network Approximation: Three Hidden Layers Are Enough Zuowei Shen Haizhao Yang Shijun Zhang 30 115 0 25 Oct 2020
The Interpolation Phase Transition in Neural Networks: Memorization and Generalization under Lazy Training Andrea Montanari Yiqiao Zhong 49 95 0 25 Jul 2020
Two-Layer Neural Networks for Partial Differential Equations: Optimization and Generalization Theory Tao Luo Haizhao Yang 32 73 0 28 Jun 2020
Can Temporal-Difference and Q-Learning Learn Representation? A Mean-Field Theory Yufeng Zhang Qi Cai Zhuoran Yang Yongxin Chen Zhaoran Wang OOD MLT 123 11 0 08 Jun 2020
Is deeper better? It depends on locality of relevant features Takashi Mori Masahito Ueda OOD 25 4 0 26 May 2020
Convergence of End-to-End Training in Deep Unsupervised Contrastive Learning Zixin Wen SSL 21 2 0 17 Feb 2020
Deep Network Approximation for Smooth Functions Jianfeng Lu Zuowei Shen Haizhao Yang Shijun Zhang 67 247 0 09 Jan 2020
Towards Understanding the Spectral Bias of Deep Learning Yuan Cao Zhiying Fang Yue Wu Ding-Xuan Zhou Quanquan Gu 41 214 0 03 Dec 2019
Gradient Descent can Learn Less Over-parameterized Two-layer Neural Networks on Classification Problems Atsushi Nitanda Geoffrey Chinot Taiji Suzuki MLT 16 33 0 23 May 2019
Global optimality conditions for deep neural networks Chulhee Yun S. Sra Ali Jadbabaie 128 117 0 08 Jul 2017
Norm-Based Capacity Control in Neural Networks Behnam Neyshabur Ryota Tomioka Nathan Srebro 127 577 0 27 Feb 2015