A lower bound on complexity of optimization on the Wiener space

Authors:
James M. Calvin
Affiliations:
Department of Computer Science, New Jersey Institute of Technology, Newark, NJ 07102, United States
Venue:
Theoretical Computer Science
Year:
2007

Citing 4
Cited 1

Information-based complexity

Information-based complexity
The real number model in numerical analysis

Journal of Complexity
Complexity and real computation

Complexity and real computation
Lower bound on complexity of optimization of continuous functions

Journal of Complexity

A lower bound on complexity of optimization under the r-fold integrated Wiener measure

Journal of Complexity

Quantified Score

Hi-index	5.23

Visualization

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, on the order of loglog(1/ε)log(1/ε) function evaluations are required.