*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
TITLE: Efficient Methods for Stochastic Composite Optimization
SPEAKER: Guanghui Lan
ABSTRACT:
We consider an important class of convex programming problems whose objective functions, given by the summation of a smooth and non-smooth component, are contaminated by stochastic noise. Although a valid lower bound on the rate of convergence for solving these problems is known from the classic complexity theory of convex programming due to Nemirovski and Yudin, the optimization algorithms that can achieve this lower bound have not been discovered. In this talk, we show that the robust stochastic approximation method exhibits the best-known rate of convergence for solving these problems. The main goal is to present the first theoretically optimal method for solving this class of problems that achieves the aforementioned lower bound on the rate of convergence and demonstrate its significant advantages over existing algorithms.
