Interface of PDEs and Machine Learning

  • Why resampling outperforms reweighting for correcting sampling bias with stochastic gradients. [pdf]

Jing An, Lexing Ying, Yuhua Zhu*.

International Conference on Learning Representations (ICLR), 2021.

  • A Sharp Convergence Rate for a Model Equation of the Asynchronous Stochastic Gradient Descent. [pdf]

Yuhua Zhu, Lexing Ying.​ 

Communications in Mathematical Sciences, 19(3), 851-863, 2020.

  • On large batch training and sharp minima: A Fokker-Planck perspective. [pdf]

Xiaowu Dai and Yuhua Zhu*.

Journal of Statistical Theory and Practice (JSTP), special issue on "Advances in Deep Learning", 2020. 

  • A consensus-based global optimization method for high dimensional machine learning problems. [pdf]

Jose Carrillo, Shi Jin, Lei Li and Yuhua Zhu*

ESAIM: Control, Optimisation and Calculus of Variations 27, S5, 2020.

  • Borrowing From the Future: An Attempt to Address Double Sampling. [pdf]

Yuhua Zhu and Lexing Ying.

Mathematical and Scientific Machine Learning, PMLR 107:246-268, 2020.