Noisy optimization convergence rates

Authors:
Sandra Astete Morales;Jialin Liu;Olivier Teytaud
Affiliations:
TAO, University of Paris-Sud, Orsay, France;TAO, University of Paris-Sud, Orsay, France;TAO, University of Paris-Sud, Orsay, France
Venue:
Proceedings of the 15th annual conference companion on Genetic and evolutionary computation
Year:
2013

Citing 4
Cited 0

The theory of evolution strategies

The theory of evolution strategies
Convergence results for the (1, λ)-SA-ES using the theory of ϕ-irreducible Markov chains

Theoretical Computer Science
Bandit-based estimation of distribution algorithms for noisy optimization: rigorous runtime analysis

LION'10 Proceedings of the 4th international conference on Learning and intelligent optimization
Lower Bounds for Comparison Based Evolution Strategies Using VC-dimension and Sign Patterns

Algorithmica - Special Issue: Theory of Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

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.