When: November 2, 2016, 12:30 PM
Location: 3rd Floor Orchard View Room , Discovery Building
Contact: 608-316-4401, firstname.lastname@example.org
Stochastic Nested Composition Optimization and Beyond
Classical stochastic optimization models usually involve expected-value objective functions. However, they do not apply to the minimization of a composition of two or multiple expected-value functions, i.e., the stochastic nested composition optimization problem. Stochastic composition optimization finds wide application in estimation, risk-averse optimization, dimension reduction and reinforcement learning. We propose a class of stochastic compositional first-order methods. We prove that the algorithms converge almost surely to an optimal solution for convex optimization problems (or a stationary point for nonconvex problems), as long as such a solution exists. The convergence involves the interplay of two martingales with different timescales. We obtain rate of convergence results under various assumptions, and show that the algorithms achieve the optimal sample-error complexity in several important special cases. These results provide the best-known rate benchmarks for stochastic composition optimization.
We demonstrate its application to statistical estimation and reinforcement learning. In addition, we also introduce some recent developments on nonconvex statistical optimization.
The weekly SILO seminar series is made possible through the generous support of the 3M Company and its Advanced Technology Group
SILO is a lecture series with speakers from the UW faculty, graduate students or invited researchers that discuss mathematical related topics. The seminars are organized by WID’s Optimization research group.
SILO’s purpose is to provide a forum that helps connect and recruit mathematically-minded graduate students. SILO is a lunch-and-listen format, where speakers present interesting math topics while the audience eats lunch.