Chao Ma

Publication Activity (10 Years)

Years Active: 2017-2024
Publications (10 Years): 37

Top Topics

Provably Convergent

Generalization Error

Machine Learning

Top Venues

Publications

Yinuo Ren, Chao Ma, Lexing Ying
Understanding the Generalization Benefits of Late Learning Rate Decay. CoRR (2024)
Yinuo Ren, Chao Ma, Lexing Ying
Understanding the Generalization Benefits of Late Learning Rate Decay. AISTATS (2024)
Chao Ma, Lexing Ying
Provably convergent quasistatic dynamics for mean-field two-player zero-sum games. CoRR (2022)
Chao Ma, Lexing Ying
Why self-attention is Natural for Sequence-to-Sequence Problems? A Perspective from Symmetries. CoRR (2022)
Chao Ma, Lexing Ying
Provably convergent quasistatic dynamics for mean-field two-player zero-sum games. ICLR (2022)
Chao Ma, Lei Wu, Lexing Ying
The Multiscale Structure of Neural Network Loss Functions: The Effect on Optimization and Origin. CoRR (2022)
Chao Ma, Lei Wu, Weinan E
A Qualitative Study of the Dynamic Behavior for Adaptive Gradient Algorithms. MSML (2021)
Chao Ma, Lexing Ying
On Linear Stability of SGD and Input-Smoothness of Neural Networks. NeurIPS (2021)
Chao Ma, Lexing Ying
The Sobolev Regularization Effect of Stochastic Gradient Descent. CoRR (2021)
Chao Ma, Lexing Ying
A Riemannian Mean Field Formulation for Two-layer Neural Networks with Batch Normalization. CoRR (2021)
Yiping Lu, Chao Ma, Yulong Lu, Jianfeng Lu, Lexing Ying
A Mean-field Analysis of Deep ResNet and Beyond: Towards Provable Optimization Via Overparameterization From Depth. CoRR (2020)
Pan Zhou, Jiashi Feng, Chao Ma, Caiming Xiong, Steven Chu-Hong Hoi, Weinan E
Towards Theoretically Understanding Why Sgd Generalizes Better Than Adam in Deep Learning. NeurIPS (2020)
Yiping Lu, Chao Ma, Yulong Lu, Jianfeng Lu, Lexing Ying
A Mean Field Analysis Of Deep ResNet And Beyond: Towards Provably Optimization Via Overparameterization From Depth. ICML (2020)
Chao Ma, Lexing Ying
Achieving Adversarial Robustness Requires An Active Teacher. CoRR (2020)
Weinan E, Chao Ma, Stephan Wojtowytsch, Lei Wu
Towards a Mathematical Understanding of Neural Network-Based Machine Learning: what we know and what we don't. CoRR (2020)
Zhong Li, Chao Ma, Lei Wu
Complexity Measures for Neural Networks with General Activation Functions Using Path-based Norms. CoRR (2020)
Pan Zhou, Jiashi Feng, Chao Ma, Caiming Xiong, Steven C. H. Hoi, Weinan E
Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning. CoRR (2020)
Chao Ma, Lei Wu, Weinan E
The Quenching-Activation Behavior of the Gradient Descent Dynamics for Two-layer Neural Network Models. CoRR (2020)
Chao Ma, Lei Wu, Weinan E
The Slow Deterioration of the Generalization Error of the Random Feature Model. CoRR (2020)
Chao Ma, Tamir Bendory, Nicolas Boumal, Fred J. Sigworth, Amit Singer
Heterogeneous Multireference Alignment for Images With Application to 2D Classification in Single Particle Reconstruction. IEEE Trans. Image Process. 29 (2020)
Chao Ma, Lei Wu, Weinan E
A Qualitative Study of the Dynamic Behavior of Adaptive Gradient Algorithms. CoRR (2020)
Chao Ma, Lei Wu, Weinan E
The Slow Deterioration of the Generalization Error of the Random Feature Model. MSML (2020)
Zehao Don, Weinan E, Chao Ma
A Priori Estimates of the Generalization Error for Autoencoders. ICASSP (2020)
Weinan E, Chao Ma, Lei Wu
Barron Spaces and the Compositional Function Spaces for Neural Network Models. CoRR (2019)
Lei Wu, Qingcan Wang, Chao Ma
Global Convergence of Gradient Descent for Deep Linear Residual Networks. CoRR (2019)
Chao Ma, Xin Liu, Zaiwen Wen
Globally Convergent Levenberg-Marquardt Method for Phase Retrieval. IEEE Trans. Inf. Theory 65 (4) (2019)
Weinan E, Chao Ma, Lei Wu
On the Generalization Properties of Minimum-norm Solutions for Over-parameterized Neural Network Models. CoRR (2019)
Weinan E, Chao Ma, Lei Wu
Machine Learning from a Continuous Viewpoint. CoRR (2019)
Weinan E, Chao Ma, Qingcan Wang, Lei Wu
Analysis of the Gradient Descent Algorithm for a Deep Neural Network Model with Skip-connections. CoRR (2019)
Weinan E, Chao Ma, Qingcan Wang
A Priori Estimates of the Population Risk for Residual Networks. CoRR (2019)
Weinan E, Chao Ma, Lei Wu
A Comparative Analysis of the Optimization and Generalization Property of Two-layer Neural Network and Random Feature Models Under Gradient Descent Dynamics. CoRR (2019)
Lei Wu, Qingcan Wang, Chao Ma
Global Convergence of Gradient Descent for Deep Linear Residual Networks. NeurIPS (2019)
Chao Ma, Jianchun Wang, Weinan E
Model Reduction with Memory and the Machine Learning of Dynamical Systems. CoRR (2018)
Lei Wu, Chao Ma, Weinan E
How SGD Selects the Global Minima in Over-parameterized Learning: A Dynamical Stability Perspective. NeurIPS (2018)
Weinan E, Chao Ma, Lei Wu
A Priori Estimates of the Generalization Error for Two-layer Neural Networks. CoRR (2018)
Tamir Bendory, Nicolas Boumal, Chao Ma, Zhizhen Zhao, Amit Singer
Bispectrum Inversion With Application to Multireference Alignment. IEEE Trans. Signal Process. 66 (4) (2018)
Tamir Bendory, Nicolas Boumal, Chao Ma, Zhizhen Zhao, Amit Singer
Bispectrum Inversion with Application to Multireference Alignment. CoRR (2017)