Random Gradient-Free Minimization of Convex Functions

Yurii Nesterov, Vladimir Spokoiny

Research output: Contribution to journalArticlepeer-review

247 Citations (Scopus)

Abstract

In this paper, we prove new complexity bounds for methods of convex optimization based only on computation of the function value. The search directions of our schemes are normally distributed random Gaussian vectors. It appears that such methods usually need at most n times more iterations than the standard gradient methods, where n is the dimension of the space of variables. This conclusion is true for both nonsmooth and smooth problems. For the latter class, we present also an accelerated scheme with the expected rate of convergence O(n2k2), where k is the iteration counter. For stochastic optimization, we propose a zero-order scheme and justify its expected rate of convergence O(nk1/2). We give also some bounds for the rate of convergence of the random gradient-free methods to stationary points of nonconvex functions, for both smooth and nonsmooth cases. Our theoretical results are supported by preliminary computational experiments.

Original languageEnglish
Pages (from-to)527-566
Number of pages40
JournalFoundations of Computational Mathematics
Volume17
Issue number2
DOIs
Publication statusPublished - 1 Apr 2017
Externally publishedYes

Keywords

  • Complexity bounds
  • Convex optimization
  • Derivative-free methods
  • Random methods
  • Stochastic optimization

Fingerprint

Dive into the research topics of 'Random Gradient-Free Minimization of Convex Functions'. Together they form a unique fingerprint.

Cite this