Non-local Optimization: Imposing Structure on Optimization Problems by Relaxation

DOI10.1145/3450218.3477307MaRDI QIDQ6353555arXivFDO

Authors Nils Müller, Tobias Glasmachers

Publication date 11 November 2020

Published in arXiv

Full work available at URL https://doi.org/10.1145/3450218.3477307

Mathematics Subject Classification ID

Computer science (68-XX) Operations research, mathematical programming (90-XX)

arXiv classification

cs.NEmath.OCstat.ML

Abstract: In stochastic optimization, particularly in evolutionary computation and reinforcement learning, the optimization of a function $f:OmegaomathbbR$ is often addressed through optimizing a so-called relaxation $hetainThetamapstomathbb{E}_{h}eta(f)$ of $f$, where $Theta$ resembles the parameters of a family of probability measures on $Omega$. We investigate the structure of such relaxations by means of measure theory and Fourier analysis, enabling us to shed light on the success of many associated stochastic optimization methods. The main structural traits we derive and that allow fast and reliable optimization of relaxations are the consistency of optimal values of $f$, Lipschitzness of gradients, and convexity. We emphasize settings where $f$ itself is not differentiable or convex, e.g., in the presence of (stochastic) disturbance.

This page was built for publication: Non-local Optimization: Imposing Structure on Optimization Problems by Relaxation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6353555)