A Stochastic Derivative Free Optimization Method with Momentum

arXiv1905.13278MaRDI QIDQ6319702FDOQ6319702

Authors: Eduard Gorbunov, Adel Bibi, Ozan Sener, El Houcine Bergou, Peter Richtárik 

Publication date: 30 May 2019

Abstract: We consider the problem of unconstrained minimization of a smooth objective function in $mathbb{R}^d$ in setting where only function evaluations are possible. We propose and analyze stochastic zeroth-order method with heavy ball momentum. In particular, we propose, SMTP, a momentum version of the stochastic three-point method (STP) cite{Bergou_2018}. We show new complexity results for non-convex, convex and strongly convex functions. We test our method on a collection of learning to continuous control tasks on several MuJoCo cite{Todorov_2012} environments with varying difficulty and compare against STP, other state-of-the-art derivative-free optimization algorithms and against policy gradient methods. SMTP significantly outperforms STP and all other methods that we considered in our numerical experiments. Our second contribution is SMTP with importance sampling which we call SMTP_IS. We provide convergence analysis of this method for non-convex, convex and strongly convex objectives.

This page was built for publication: A Stochastic Derivative Free Optimization Method with Momentum

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6319702)