Timezone: »

 
Poster
Stochastic Primal-Dual Method for Empirical Risk Minimization with O(1) Per-Iteration Complexity
Conghui Tan · Tong Zhang · Shiqian Ma · Ji Liu

Wed Dec 05 07:45 AM -- 09:45 AM (PST) @ Room 210 #13
in Wed Poster Session A »

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 this class of problems. Different from existing methods, our proposed methods only require O(1) operations in each iteration. We also develop a variance-reduction variant of the algorithm that converges linearly. Numerical experiments suggest that our methods are faster than existing ones such as proximal SGD, SVRG and SAGA on high-dimensional problems.

Keywords: Convex Optimization
[ Paper] 

Author Information

Conghui Tan (The Chinese University of Hong Kong)
Tong Zhang (Tencent AI Lab)
Shiqian Ma
Ji Liu (University of Rochester, Tencent AI lab)

More from the Same Authors