Noisy optimization convergence rates
Lists
Only you see this
Abstract
We consider noisy optimization problems, without the assumption of variance vanishing in the neighborhood of the optimum. We show mathematically that evolutionary algorithms with simple rules with exponential number of resamplings lead to a log-log convergence rate (log of the distance to the optimum linear in the log of the number of resamplings), as well as with number of resamplings polynomial in the inverse step-size.
BibTeX
@inproceedings{morales2013noisy,
author = {Sandra Astete Morales and Jialin Liu and Olivier Teytaud},
title = {{Noisy optimization convergence rates}},
booktitle = {GECCO (Companion)},
year = {2013},
doi = {10.1145/2464576.2464687},
}Loading related content...