Analysis of Different Types of Regret in Continuous Noisy Optimization - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Analysis of Different Types of Regret in Continuous Noisy Optimization

Résumé

The performance measure of an algorithm is a crucial part of its analysis. The performance can be determined by the study on the convergence rate of the algorithm in question. It is necessary to study some (hopefully convergent) sequence that will measure how " good " is the approximated optimum compared to the real optimum. The concept of Regret is widely used in the bandit literature for assessing the performance of an algorithm. The same concept is also used in the framework of optimization algorithms, sometimes under other names or without a specific name. And the numerical evaluation of convergence rate of noisy algorithms often involves approximations of regrets. We discuss here two types of approximations of Simple Regret used in practice for the evaluation of algorithms for noisy optimization. We use specific algorithms of different nature and the noisy sphere function to show the following results. The approximation of Simple Regret, termed here Approximate Simple Regret, used in some optimization testbeds, fails to estimate the Simple Regret convergence rate. We also discuss a recent new approximation of Simple Regret, that we term Robust Simple Regret, and show its advantages and disadvantages.
Fichier principal
Vignette du fichier
asrHAL.pdf (455.46 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01347814 , version 1 (21-07-2016)
hal-01347814 , version 2 (23-07-2016)

Identifiants

Citer

Sandra Astete-Morales, Marie-Liesse Cauwet, Olivier Teytaud. Analysis of Different Types of Regret in Continuous Noisy Optimization. Genetic and Evolutionary Computation Conference 2016, Jul 2016, Denver, United States. pp.205-212. ⟨hal-01347814v2⟩
201 Consultations
164 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More