399 citations · 3.4k across the 95 of their papers we have counts for
Showing 2018 · math.OCShow all
3 papers · 2 filters
math.OC2018
Stochastic Primal-Dual Method for Empirical Risk Minimization with Per-Iteration Complexity
Conghui Tan, Tong Zhang, Shiqian Ma +1
Regularized empirical risk minimization problem with linear predictor appears frequently in machine learning. In this paper, we propose a new stochastic primal-dual method to solve…
math.OC2018★ 3 cited
Revisit Batch Normalization: New Understanding from an Optimization View and a Refinement via Composition Optimization
Xiangru Lian, Ji Liu
Batch Normalization (BN) has been used extensively in deep learning to achieve faster training process and better resulting models. However, whether BN works strongly depends on ho…
math.OC2018★ 9 cited
Stochastically Controlled Stochastic Gradient for the Convex and Non-convex Composition problem
Liu Liu, Ji Liu, Cho-Jui Hsieh +1
In this paper, we consider the convex and non-convex composition problem with the structure , where $G( x )=\frac{1}{n}\sum\…