EURO-Online login
- New to EURO? Create an account
- I forgot my username and/or my password.
- Help with cookies
(important for IE8 users)
963. An interior proximal gradient method for nonconvex optimization
Invited abstract in session TA-32: Nonsmooth optimization and applications, Part I, stream Advances in large scale nonlinear optimization.
Tuesday, 8:30-10:00Room: 41 (building: 303A)
Authors (first author is the speaker)
| 1. | Alberto De Marchi
|
| University of the Bundeswehr Munich | |
| 2. | Andreas Themelis
|
| Information Science and Electrical Engineering, Kyushu University |
Abstract
We consider structured minimization problems subject to smooth inequality constraints and present a flexible algorithm that combines interior point (IP) and proximal gradient schemes. While traditional IP methods cannot cope with nonsmooth objective functions and proximal algorithms cannot handle complicated constraints, their combined usage is shown to successfully compensate the respective shortcomings. We provide a theoretical characterization of the algorithm and its asymptotic properties, deriving convergence results for fully nonconvex problems, thus bridging the gap with previous works that successfully addressed the convex case. Our interior proximal gradient algorithm benefits from warm starting, generates strictly feasible iterates with decreasing objective value, and returns after finitely many iterations a primal-dual pair approximately satisfying suitable optimality conditions. As a byproduct of our analysis of proximal gradient iterations we demonstrate that a slight refinement of traditional backtracking techniques waives the need for upper bounding the stepsize sequence, as required in existing results for the nonconvex setting.
Keywords
- Non-smooth Optimization
- Large Scale Optimization
- Interior Point Methods
Status: accepted
Back to the list of papers