The system will be going down for regular maintenance. Please save your work and logout.
FISTA is an automatic geometrically optimized algorithm for strongly convex functions
Language
en
Document de travail - Pré-publication
English Abstract
In this work, we are interested in the famous FISTA algorithm. We show that FISTA is an automatic geometrically optimized algorithm for functions satisfying a quadratic growth assumption. This explains why FISTA works ...Read more >
In this work, we are interested in the famous FISTA algorithm. We show that FISTA is an automatic geometrically optimized algorithm for functions satisfying a quadratic growth assumption. This explains why FISTA works better than the standard Forward-Backward algorithm (FB) in such a case, although FISTA is known to have a polynomial asymptotical convergence rate while FB is exponential. We provide a simple rule to tune the α parameter within the FISTA algorithm to reach an ε-solution with an optimal number of iterations. These new results highlight the efficiency of FISTA algorithms, and they rely on new non asymptotic bounds for FISTA.Read less <
English Keywords
Nesterov acceleration
ODE
first order scheme
optimization
Origin
Hal imported