A lower bound on complexity of optimization on the Wiener space

Document Type

Article

Publication Date

9-18-2007

Abstract

This paper is a study of the complexity of optimization of continuous univariate functions using a fixed number of sequentially selected function evaluations. The complexity is studied in the average case under a conditioned Wiener measure. We show that to obtain an error of at most ε{lunate}, on the order of log log (1 / ε{lunate}) log (1 / ε{lunate}) function evaluations are required. © 2007 Elsevier Ltd. All rights reserved.

Identifier

34548130697 (Scopus)

Publication Title

Theoretical Computer Science

External Full Text Location

https://doi.org/10.1016/j.tcs.2007.04.016

ISSN

03043975

First Page

132

Last Page

139

Issue

2-3

Volume

383

This document is currently not available here.

Share

COinS