research
∙
05/19/2022
Mean-Field Analysis of Two-Layer Neural Networks: Global Optimality with Linear Convergence Rates
We consider optimizing two-layer neural networks in the mean-field regim...
share
research
∙
06/12/2020
ACMo: Angle-Calibrated Moment Methods for Stochastic Optimization
Due to its simplicity and outstanding ability to generalize, stochastic ...
research
∙
06/12/2020
Adaptive Gradient Methods Can Be Provably Faster than SGD after Finite Epochs
Adaptive gradient methods have attracted much attention of machine learn...
research
∙
02/10/2020
SPAN: A Stochastic Projected Approximate Newton Method
Second-order optimization methods have desirable convergence properties....
research
∙
11/11/2017