Accelerated Method for Stochastic Composition Optimization with Nonsmooth Regularization
Accelerated Method for Stochastic Composition Optimization with Nonsmooth Regularization
复制标题
DOI：
10.1609/aaai.v32i1.11795
复制
发表时间：
2017-11
期刊：
影响因子：
--
通讯作者：
Zhouyuan Huo;Bin Gu;Heng Huang
中科院分区：
文献类型：
--
作者：
Zhouyuan Huo;Bin Gu;Heng Huang
随机组成的优化最近引起了很多关注，并且在机器学习，统计分析和加强学习的许多新兴应用中都取得了成功。请勿在本文中为一般问题提供完整的融合分析非平滑惩罚的组成问题的优化方法。 ，我们的算法被证明是一般组成问题的线性融合，我们的算法显着提高了最新的收敛速度o（t – 1/2）o（（n1+n2）2/3T-1）。
Stochastic composition optimization draws much attention recently and has been successful in many emerging applications of machine learning, statistical analysis, and reinforcement learning. In this paper, we focus on the composition problem with nonsmooth regularization penalty. Previous works either have slow convergence rate, or do not provide complete convergence analysis for the general problem. In this paper, we tackle these two issues by proposing a new stochastic composition optimization method for composition problem with nonsmooth regularization penalty. In our method, we apply variance reduction technique to accelerate the speed of convergence. To the best of our knowledge, our method admits the fastest convergence rate for stochastic composition optimization: for strongly convex composition problem, our algorithm is proved to admit linear convergence; for general composition problem, our algorithm significantly improves the state-of-the-art convergence rate from O(T–1/2) to O((n1+n2)2/3T-1). Finally, we apply our proposed algorithm to portfolio management and policy evaluation in reinforcement learning. Experimental results verify our theoretical analysis.