Presented By: Department of Mathematics
Asymptotic normality and optimality in nonsmooth stochastic approximation
Dima Drusvyatskiy (University of Washington)
In their seminal work, Polyak and Juditsky showed that stochastic approximation algorithms for solving smooth equations enjoy a central limit theorem. Moreover, it has since been argued that the asymptotic covariance of the method is best possible among any estimation procedure in a local minimax sense of H´ajek and Le Cam. A long-standing open question in this line of work is whether similar guarantees hold for important non-smooth problems, such as stochastic nonlinear programming or stochastic variational inequalities. In this work, we show that this is indeed the case. This is joint work with Damek Davis and Liwei Jiang.
Livestream Information
ZoomMarch 10, 2023 (Friday) 9:00am
Meeting ID: 92332350184
Meeting Password: 123456
Explore Similar Events
-
Loading Similar Events...
