Chao Ma

Orcid: 0000-0002-8901-960X

Affiliations:
  • Stanford University, Department of Mathematics, Stanford, CA, USA
  • Princeton University, Program in Applied and Computational Mathematics, Princeton, NJ, USA (PhD 2020)


According to our database1, Chao Ma authored at least 30 papers between 2018 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Understanding the Generalization Benefits of Late Learning Rate Decay.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2022
Why self-attention is Natural for Sequence-to-Sequence Problems? A Perspective from Symmetries.
CoRR, 2022

The Multiscale Structure of Neural Network Loss Functions: The Effect on Optimization and Origin.
CoRR, 2022

Provably convergent quasistatic dynamics for mean-field two-player zero-sum games.
Proceedings of the Tenth International Conference on Learning Representations, 2022

2021
A Riemannian Mean Field Formulation for Two-layer Neural Networks with Batch Normalization.
CoRR, 2021

The Sobolev Regularization Effect of Stochastic Gradient Descent.
CoRR, 2021

On Linear Stability of SGD and Input-Smoothness of Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

A Qualitative Study of the Dynamic Behavior for Adaptive Gradient Algorithms.
Proceedings of the Mathematical and Scientific Machine Learning, 2021

2020
Heterogeneous Multireference Alignment for Images With Application to 2D Classification in Single Particle Reconstruction.
IEEE Trans. Image Process., 2020

Achieving Adversarial Robustness Requires An Active Teacher.
CoRR, 2020

Towards a Mathematical Understanding of Neural Network-Based Machine Learning: what we know and what we don't.
CoRR, 2020

Complexity Measures for Neural Networks with General Activation Functions Using Path-based Norms.
CoRR, 2020

The Quenching-Activation Behavior of the Gradient Descent Dynamics for Two-layer Neural Network Models.
CoRR, 2020

A Mean-field Analysis of Deep ResNet and Beyond: Towards Provable Optimization Via Overparameterization From Depth.
CoRR, 2020

Towards Theoretically Understanding Why Sgd Generalizes Better Than Adam in Deep Learning.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

The Slow Deterioration of the Generalization Error of the Random Feature Model.
Proceedings of Mathematical and Scientific Machine Learning, 2020

A Mean Field Analysis Of Deep ResNet And Beyond: Towards Provably Optimization Via Overparameterization From Depth.
Proceedings of the 37th International Conference on Machine Learning, 2020

A Priori Estimates of the Generalization Error for Autoencoders.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2019
Globally Convergent Levenberg-Marquardt Method for Phase Retrieval.
IEEE Trans. Inf. Theory, 2019

Machine Learning from a Continuous Viewpoint.
CoRR, 2019

On the Generalization Properties of Minimum-norm Solutions for Over-parameterized Neural Network Models.
CoRR, 2019

Barron Spaces and the Compositional Function Spaces for Neural Network Models.
CoRR, 2019

Analysis of the Gradient Descent Algorithm for a Deep Neural Network Model with Skip-connections.
CoRR, 2019

A Comparative Analysis of the Optimization and Generalization Property of Two-layer Neural Network and Random Feature Models Under Gradient Descent Dynamics.
CoRR, 2019

A Priori Estimates of the Population Risk for Residual Networks.
CoRR, 2019

Global Convergence of Gradient Descent for Deep Linear Residual Networks.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

2018
Bispectrum Inversion With Application to Multireference Alignment.
IEEE Trans. Signal Process., 2018

A Priori Estimates of the Generalization Error for Two-layer Neural Networks.
CoRR, 2018

Model Reduction with Memory and the Machine Learning of Dynamical Systems.
CoRR, 2018

How SGD Selects the Global Minima in Over-parameterized Learning: A Dynamical Stability Perspective.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018


  Loading...