poster

Optimal robust expensive optimization is tractable

Authors:

Philippe Rolet,

Michèle Sebag,

Olivier TeytaudAuthors Info & Claims

GECCO '09: Proceedings of the 11th Annual conference on Genetic and evolutionary computation

Pages 1951 - 1956

https://doi.org/10.1145/1569901.1570255

Published: 08 July 2009 Publication History

Get Access

Abstract

Following a number of recent papers investigating the possibility of optimal comparison-based optimization algorithms for a given distribution of probability on fitness functions, we (i) discuss the comparison-based constraints (ii) choose a setting in which theoretical tight bounds are known (iii) develop a careful implementation using billiard algorithms, Upper Confidence trees and (iv) experimentally test the tractability of the approach. The results, on still very simple cases, show that the approach, yet still preliminary, could be tested successfully until dimension 10 and horizon 50 iterations within a few hours on a standard computer, with convergence rate far better than the best algorithms.

References

[1]

]]A. Auger and O. Teytaud. Continuous lunches are free plus the design of optimal optimization algorithms. Algorithmica, Accepted.

Digital Library

Google Scholar

[2]

]]S. Gelly, S. Ruette, and O. Teytaud. Comparison-based algorithms: worst-case optimality, optimality w.r.t a bayesian prior, the intraclass-variance minimization in eda, and implementations with billiards. In PPSN--BTP workshop, 2006.

Google Scholar

[3]

]]R. Herbrich, T. Graepel, and C. Campbell. Bayes point machines. Journal of Machine Learning Research, 1:245--279, 2001.

Digital Library

Google Scholar

[4]

]]D. R. Jones, M. Schonlau, and W. J. Welch. Efficient global optimization of expensive black-box functions. J. of Global Optimization, 13(4):455--492, 1998.

Digital Library

Google Scholar

[5]

]]L. Kocsis and C. Szepesvari. Bandit-based monte-carlo planning. In ECML'06, pages 282--293, 2006.

Digital Library

Google Scholar

[6]

]]T.-P. Runarsson. Ordinal regression in evolutionary computation. In proceedings of PPSN, pages 1048--1057, 2006.

Digital Library

Google Scholar

[7]

]]O. Teytaud and H. Fournier. Lower bounds for evolution strategies using VC-dimension. In G. Rudolph, T. Jansen, S. M. Lucas, C. Poloni, and N. Beume, editors, PPSN, volume 5199 of Lecture Notes in Computer Science, pages 102--111. Springer, 2008.

Google Scholar

[8]

]]O. Teytaud and S. Gelly. General lower bounds for evolutionary computation. In proceedings of PPSN, 2006.

Digital Library

Google Scholar

[9]

]]E. Vazquez, J. Villemonteix, M. Sidorkiewicz, and E. Walter. Global optimization based on noisy evaluations: an empirical study of two statistical approaches. Journal of Global Optimization, page 17 pages, 2008.

Google Scholar

[10]

]]J. Villemonteix, E. Vazquez, and E. Walter. An informational approach to the global optimization of expensive-to-evaluate functions. Journal of Global Optimization, page 26 pages, 09 2008.

Digital Library

Google Scholar

[11]

]]Z. Zhou. Hierarchical surrogate-assisted evolutionary optimization framework. In In Evolutionary Computation, 2004. CEC2004. Congress on, pages 1586--1593, 2004.

Google Scholar

Cited By

View all

Bouzy BCazenave TCorruble VTeytaud O(2020)Artificial Intelligence for GamesA Guided Tour of Artificial Intelligence Research10.1007/978-3-030-06167-8_11(313-337)Online publication date: 8-May-2020
https://doi.org/10.1007/978-3-030-06167-8_11
Lockett AArnold D(2014)Model-optimal optimization by solving bellman equationsProceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation10.1145/2576768.2598306(1407-1414)Online publication date: 12-Jul-2014
https://dl.acm.org/doi/10.1145/2576768.2598306
Teytaud OVazquez E(2013)Designing an Optimal Search Algorithm with Respect to Prior InformationTheory and Principled Methods for the Design of Metaheuristics10.1007/978-3-642-33206-7_6(111-128)Online publication date: 12-Nov-2013
https://doi.org/10.1007/978-3-642-33206-7_6
Show More Cited By

Index Terms

Optimal robust expensive optimization is tractable
1. Mathematics of computing
  1. Mathematical analysis
    1. Mathematical optimization
2. Theory of computation
  1. Design and analysis of algorithms
    1. Mathematical optimization

Recommendations

A metamodel-assisted evolutionary algorithm for expensive optimization

Expensive optimization aims to find the global minimum of a given function within a very limited number of function evaluations. It has drawn much attention in recent years. The present expensive optimization algorithms focus their attention on ...
A multi-strategy surrogate-assisted social learning particle swarm optimization for expensive optimization and applications
Abstract
Evolutionary algorithms (EAs) require extensive fitness evaluations, which constitutes a barrier to solving computationally complex problems. In contrast, surrogate-assisted evolutionary algorithms (SAEAs) have the potential to solve complex ...
Highlights
- SASLPSO is proposed to solve expensive optimization problems.
- A novel RGBPS strategy is proposed to screen promising particles.
- An adaptive local surrogate (ALS) is proposed to local fitting.
- The proposed SASLPSO effectively ...
sParEGO – A Hybrid Optimization Algorithm for Expensive Uncertain Multi-objective Optimization Problems
Evolutionary Multi-Criterion Optimization
Abstract
Evaluations of candidate solutions to real-world problems are often expensive to compute, are characterised by uncertainties arising from multiple sources, and involve simultaneous consideration of multiple conflicting objectives. Here, the task ...

Comments

Information & Contributors

Information

Published In

GECCO '09: Proceedings of the 11th Annual conference on Genetic and evolutionary computation

July 2009

2036 pages

ISBN:9781605583259

DOI:10.1145/1569901

General Chair:
Franz Rothlauf
University of Mainz, Germany

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 08 July 2009

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Poster

Conference

GECCO09

Sponsor:

GECCO09: Genetic and Evolutionary Computation Conference

July 8 - 12, 2009

Québec, Montreal, Canada

Acceptance Rates

Overall Acceptance Rate 1,669 of 4,410 submissions, 38%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

8
Total Citations
View Citations
114
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 06 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Bouzy BCazenave TCorruble VTeytaud O(2020)Artificial Intelligence for GamesA Guided Tour of Artificial Intelligence Research10.1007/978-3-030-06167-8_11(313-337)Online publication date: 8-May-2020
https://doi.org/10.1007/978-3-030-06167-8_11
Lockett AArnold D(2014)Model-optimal optimization by solving bellman equationsProceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation10.1145/2576768.2598306(1407-1414)Online publication date: 12-Jul-2014
https://dl.acm.org/doi/10.1145/2576768.2598306
Teytaud OVazquez E(2013)Designing an Optimal Search Algorithm with Respect to Prior InformationTheory and Principled Methods for the Design of Metaheuristics10.1007/978-3-642-33206-7_6(111-128)Online publication date: 12-Nov-2013
https://doi.org/10.1007/978-3-642-33206-7_6
Sebag MTeytaud O(2012)Upper Confidence Tree-Based Consistent Reactive Planning Application to MineSweeperRevised Selected Papers of the 6th International Conference on Learning and Intelligent Optimization - Volume 721910.5555/2961491.2961508(220-234)Online publication date: 16-Jan-2012
https://dl.acm.org/doi/10.5555/2961491.2961508
Browne CPowley EWhitehouse DLucas SCowling PRohlfshagen PTavener SPerez DSamothrakis SColton S(2012)A Survey of Monte Carlo Tree Search MethodsIEEE Transactions on Computational Intelligence and AI in Games10.1109/TCIAIG.2012.21868104:1(1-43)Online publication date: Mar-2012
https://doi.org/10.1109/TCIAIG.2012.2186810
Sebag MTeytaud O(2012)Upper Confidence Tree-Based Consistent Reactive Planning Application to MineSweeperLearning and Intelligent Optimization10.1007/978-3-642-34413-8_16(220-234)Online publication date: 2012
https://doi.org/10.1007/978-3-642-34413-8_16
Berthier VDoghmen HTeytaud O(2010)Consistency modifications for automatically tuned Monte-Carlo tree searchProceedings of the 4th international conference on Learning and intelligent optimization10.5555/1893659.1893669(111-124)Online publication date: 18-Jan-2010
https://dl.acm.org/doi/10.5555/1893659.1893669
Berthier VDoghmen HTeytaud O(2010)Consistency Modifications for Automatically Tuned Monte-Carlo Tree SearchLearning and Intelligent Optimization10.1007/978-3-642-13800-3_9(111-124)Online publication date: 2010
https://doi.org/10.1007/978-3-642-13800-3_9

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

A metamodel-assisted evolutionary algorithm for expensive optimization

A multi-strategy surrogate-assisted social learning particle swarm optimization for expensive optimization and applications

sParEGO – A Hybrid Optimization Algorithm for Expensive Uncertain Multi-objective Optimization Problems