Variational Analysis and Optimization Seminar
A Bregman inertial forward-reflected-backward method for nonconvex minimization
Friday, September 30, 2022
9:00-10:00 AM
Off Campus Location
We propose a Bregman inertial forward-reflected-backward method for nonconvex composite problems. Our analysis relies on a novel approach that imposes general conditions on implicit merit function parameters, which yields a stepsize condition that is independent of inertial parameters. In turn, a question of Malitsky and Tam regarding whether FRB can be equipped with a Nesterov-type acceleration is resolved. Assuming the generalized concave Kurdyka-Lojasiewicz property of a quadratic regularization of the objective, we obtain sequential convergence as well as convergence rates on both the function value and actual sequence. Joint work with Ziyuan Wang Speaker(s): Shawn Wang (University of British Columbia - Canada)
Building: | Off Campus Location |
---|---|
Location: | Virtual |
Event Type: | Workshop / Seminar |
Tags: | Mathematics |
Source: | Happening @ Michigan from Department of Mathematics, Variational Analysis and Optimization Seminar - Department of Mathematics |