Stabilized SVRG: Simple Variance Reduction for Nonconvex Optimization

• المؤلفون الرئيسيون: GE, Rong, LI, Zhize, WANG, Weiyao, WANG, Xiang
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2019
• الموضوعات: Databases and Information Systems
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/sis_research/8677; https://ink.library.smu.edu.sg/context/sis_research/article/9680/viewcontent/COLT19_stabilizedsvrg.pdf
• المؤسسة: Singapore Management University

Variance reduction techniques like SVRG provide simple and fast algorithms for optimizing a convex finite-sum objective. For nonconvex objectives, these techniques can also find a first-order stationary point (with small gradient). However, in nonconvex optimization it is often crucial to find a sec...