event

Efficient Methods for Stochastic Composite Optimization

Primary tabs

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.

Status

  • Workflow Status:Published
  • Created By:Anita Race
  • Created:10/12/2009
  • Modified By:Fletcher Moore
  • Modified:10/07/2016