Proxy Convexity: A Unified Framework for the Analysis of Neural Networks Trained by Gradient Descent

25 June 2021

Quanquan Gu

Papers citing "Proxy Convexity: A Unified Framework for the Analysis of Neural Networks Trained by Gradient Descent"

21 / 21 papers shown

Title
Optimal Hessian/Jacobian-Free Nonconvex-PL Bilevel Optimization Feihu Huang 44 4 0 25 Jul 2024
Almost sure convergence rates of stochastic gradient methods under gradient domination Simon Weissmann Sara Klein Waïss Azizian Leif Döring 34 3 0 22 May 2024
Implicit Bias and Fast Convergence Rates for Self-attention Bhavya Vasudeva Puneesh Deora Christos Thrampoulidis 26 13 0 08 Feb 2024
Adaptive Mirror Descent Bilevel Optimization Feihu Huang 33 1 0 08 Nov 2023
On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic Approximation Jeongyeol Kwon Dohyun Kwon Steve Wright Robert D. Nowak 26 25 0 04 Sep 2023
A Linearly Convergent GAN Inversion-based Algorithm for Reverse Engineering of Deceptions D. Thaker Paris V. Giampouras René Vidal AAML 24 0 0 07 Jun 2023
Implicit Regularization in Feedback Alignment Learning Mechanisms for Neural Networks Zachary Robertson Oluwasanmi Koyejo 23 0 0 02 Jun 2023
Benign Overfitting for Two-layer ReLU Convolutional Neural Networks Yiwen Kou Zi-Yuan Chen Yuanzhou Chen Quanquan Gu MLT 49 12 0 07 Mar 2023
On Momentum-Based Gradient Methods for Bilevel Optimization with Nonconvex Lower-Level Feihu Huang 24 18 0 07 Mar 2023
Enhanced Adaptive Gradient Algorithms for Nonconvex-PL Minimax Optimization Feihu Huang Chunyu Xuan Xinrui Wang Siqi Zhang Songcan Chen 28 7 0 07 Mar 2023
On the Convergence of the Gradient Descent Method with Stochastic Fixed-point Rounding Errors under the Polyak-Lojasiewicz Inequality Lu Xia M. Hochstenbach Stefano Massei 27 2 0 23 Jan 2023
Generalized Gradient Flows with Provable Fixed-Time Convergence and Fast Evasion of Non-Degenerate Saddle Points Mayank Baranwal Param Budhraja V. Raj A. Hota 30 2 0 07 Dec 2022
Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data Spencer Frei Gal Vardi Peter L. Bartlett Nathan Srebro Wei Hu MLT 28 38 0 13 Oct 2022
BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach Mao Ye B. Liu S. Wright Peter Stone Qian Liu 72 82 0 19 Sep 2022
On Feature Learning in Neural Networks with Global Convergence Guarantees Zhengdao Chen Eric Vanden-Eijnden Joan Bruna MLT 28 12 0 22 Apr 2022
From Optimization Dynamics to Generalization Bounds via Łojasiewicz Gradient Inequality Fusheng Liu Haizhao Yang Soufiane Hayou Qianxiao Li AI4CE 11 2 0 22 Feb 2022
Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data Spencer Frei Niladri S. Chatterji Peter L. Bartlett MLT 37 69 0 11 Feb 2022
Global convergence of ResNets: From finite to infinite width using linear parameterization Raphael Barboni Gabriel Peyré Franccois-Xavier Vialard 16 12 0 10 Dec 2021
Self-training Converts Weak Learners to Strong Learners in Mixture Models Spencer Frei Difan Zou Zixiang Chen Quanquan Gu 25 17 0 25 Jun 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 18 0 04 Jan 2021
Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Łojasiewicz Condition Hamed Karimi J. Nutini Mark W. Schmidt 133 1,198 0 16 Aug 2016