research-article

Warm starting Bayesian optimization

Authors:

Matthias Poloczek,

Peter I. FrazierAuthors Info & Claims

WSC '16: Proceedings of the 2016 Winter Simulation Conference

Pages 770 - 781

Published: 11 December 2016 Publication History

Abstract

We develop a framework for warm-starting Bayesian optimization, that reduces the solution time required to solve an optimization problem that is one in a sequence of related problems. This is useful when optimizing the output of a stochastic simulator that fails to provide derivative information, for which Bayesian optimization methods are well-suited. Solving sequences of related optimization problems arises when making several business decisions using one optimization model and input data collected over different time periods or markets. While many gradient-based methods can be warm started by initiating optimization at the solution to the previous problem, this warm start approach does not apply to Bayesian optimization methods, which carry a full metamodel of the objective function from iteration to iteration. Our approach builds a joint statistical model of the entire collection of related objective functions, and uses a value of information calculation to recommend points to evaluate.

References

[1]

Banerjee, A., D. B. Dunson, and S. T. Tokdar. 2012. "Efficient Gaussian Process Regression for Large Datasets". Biometrika 100 (1): 75--89.

[2]

Brochu, E., V. M. Cora, and N. de Freitas. 2009. "A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning". Technical Report TR-2009-23, Department of Computer Science, University of British Columbia.

[3]

Chick, S. E. 2000. "Bayesian Methods: Bayesian Methods for Simulation". In Proceedings of the 2000 Winter Simulation Conference, edited by J. A. Joines, R. R. Barton, K. Kang, and P. A. Fishwick, 109--118. San Diego, CA, USA: Society for Computer Simulation International.

Digital Library

[4]

Feurer, M., J. T. Springenberg, and F. Hutter. 2014. "Using Meta-Learning to Initialize Bayesian Optimization of Hyperparameters". In Proceedings of the International Workshop on Meta-Learning and Algorithm Selection (ECAI), 3--10.

Digital Library

[5]

Flaxman, S., A. G. Wilson, D. B. Neill, H. Nickisch, and A. J. Smola. 2015. "Fast Kronecker Inference in Gaussian Processes with Non-Gaussian Likelihoods". In Proceedings of the 32nd International Conference on Machine Learning, 607--616.

[6]

Frazier, P. I. 2011. "Decision-Theoretic Foundations of Simulation Optimization". In Wiley Encyclopedia of Operations Research and Management Science. John Wiley and Sons.

[7]

Frazier, P. I., W. B. Powell, and S. Dayanik. 2009. "The Knowledge Gradient Policy for Correlated Normal Beliefs". INFORMS Journal on Computing 21 (4): 599--613.

[8]

Frazier, P. I., and J. Wang. 2016. "Bayesian Optimization for Materials Design". In Information Science for Materials Discovery and Design, 45--75.

[9]

Frazier, P. I., J. Xie, and S. E. Chick. 2011. "Value of Information Methods for Pairwise Sampling with Correlations". In Proceedings of the 2011 Winter Simulation Conference, edited by S. Jain, R. Creasey, and J. Himmelspach, 3979--3991. Phoenix, AZ, USA: Society for Computer Simulation International.

Digital Library

[10]

Gano, S. E., J. E. Renaud, and B. Sanders. 2004. "Variable Fidelity Optimization using a Kriging Based Scaling Function". In Proceedings of the Tenth AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference.

[11]

Geppert, L. N., K. Ickstadt, A. Munteanu, J. Quedenfeld, and C. Sohler. 2015. "Random Projections for Bayesian Regression". Statistics and Computing:1--23.

[12]

Glavic, M., and L. Wehenkel. 2004. "Interior Point Methods: A Survey, Short Survey of Applications to Power Systems, and Research Opportunities". Technical report, Department of Electrical Engineering and Computer Science, Universite de Liège, Sart Tilman, Belgium.

[13]

Hong, L. J., and B. L. Nelson. 2006. "Discrete Optimization via Simulation using COMPASS". Operations Research 54 (1): 115--129.

Digital Library

[14]

John, E., and E. A. Yildirim. 2008. "Implementation of Warm-Start Strategies in Interior-Point Methods for Linear Programming in Fixed Dimension". Computational Optimization and Applications 41 (2): 151--183.

Digital Library

[15]

Jones, D. R., M. Schonlau, and W. J. Welch. 1998. "Efficient Global Optimization of Expensive Black-Box Functions". Journal of Global Optimization 13 (4): 455--492.

Digital Library

[16]

Kailath, T. 1968. "An Innovations Approach to Least-Squares Estimation - Part I: Linear Filtering in Additive White Noise". IEEE Transactions on Automatic Control 13 (6): 646--655.

[17]

Kleijnen, J. P. 2014. "Simulation-Optimization via Kriging and Bootstrapping: A Survey". Journal of Simulation 8 (4): 241--250.

[18]

Poloczek, M., J. Wang, and P. I. Frazier. 2016. "Multi-Information Source Optimization with General Model Discrepancies". ArXiv e-print 1603.00389. Available via http://arxiv.org/abs/1603.00389.

[19]

Rasmussen, C. E., and C. K. I. Williams. 2006. Gaussian Processes for Machine Learning. MIT Press.

Digital Library

[20]

Swersky, K., J. Snoek, and R. P. Adams. 2013. "Multi-Task Bayesian Optimization". In Advances in Neural Information Processing Systems, 2004--2012.

Digital Library

[21]

Wilson, A. G., and H. Nickisch. 2015. "Kernel Interpolation for Scalable Structured Gaussian Processes (KISS-GP)". In Proceedings of the 32nd International Conference on Machine Learning, 1775--1784.

[22]

Xie, J. and Frazier, P. I. and Chick, S. 2012. "Assemble to Order Simulator". http://simopt.org/wiki/index.php?title=Assemble_to_Order&oldid=447. Accessed May 9, 2016.

[23]

Yildirim, E. A., and S. J. Wright. 2002. "Warm-Start Strategies in Interior-Point Methods for Linear Programming". SIAM Journal on Optimization 12 (3): 782--810.

Digital Library

Cited By

Truger FBarzen JBechtold MBeisel MLeymann FMandl AYussupov V(2024)Warm-Starting and Quantum Computing: A Systematic Mapping StudyACM Computing Surveys10.1145/365251056:9(1-31)Online publication date: 13-Mar-2024
https://dl.acm.org/doi/10.1145/3652510
He LShanbhag USong E(2023)Stochastic Approximation for Multi-period Simulation Optimization with Streaming Input DataACM Transactions on Modeling and Computer Simulation10.1145/3617595Online publication date: 29-Aug-2023
https://dl.acm.org/doi/10.1145/3617595
Chen YSong XLee CWang ZZhang QDohan DKawakami KKochanski GDoucet ARanzato MPerel Sde Freitas NKoyejo SMohamed SAgarwal ABelgrave DCho KOh A(2022)Towards learning universal hyperparameter optimizers with transformersProceedings of the 36th International Conference on Neural Information Processing Systems10.5555/3600270.3602593(32053-32068)Online publication date: 28-Nov-2022
https://dl.acm.org/doi/10.5555/3600270.3602593
Show More Cited By

Warm starting Bayesian optimization
1. Computing methodologies
2. Theory of computation
  1. Design and analysis of algorithms

Recommendations

Intuitionistic fuzzy estimation of the ant colony optimization starting points
LSSC'11: Proceedings of the 8th international conference on Large-Scale Scientific Computing

The ability of ant colonies to form paths for carrying food is rather fascinating. The problem is solved collectively by the whole colony. This ability is explained by the fact that ants communicate in an indirect way by laying trails of pheromone. The ...
A new particle swarm optimization algorithm with adaptive inertia weight based on Bayesian techniques

Graphical abstractA new particle swarm optimization algorithm based on the Bayesian techniques(BPSO) is proposed. Fig. 1 is the comparisons between different inertia weight strategies for f5 on 10 dimensions. Fig. 2 is comparisons between different PSO ...
An enhanced particle swarm optimization with levy flight for global optimization

Enhanced PSO with levy flight.Random walk of the particles.High convergence rate.Provides solution accuracy and robust. Hüseyin Haklı and Harun Uguz (2014) proposed a novel approach for global function optimization using particle swarm optimization with ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

WSC '16: Proceedings of the 2016 Winter Simulation Conference

December 2016

3974 pages

ISBN:9781509044849

General Chair:
Todd Huschka
Mayo Clinic
,
Program Chair:
Stephen E. Chick
INSEAD

Sponsors

IIE: Institute of Industrial Engineers
INFORMS-SIM: Institute for Operations Research and the Management Sciences: Simulation Society
SIGSIM: ACM Special Interest Group on Simulation and Modeling
SCS: Society for Modeling and Simulation International

In-Cooperation

SAS
AnyLogic: The AnyLogic Company
Palgrave: Palgrave Macmillan
FlexSim: FlexSim Software Products, Inc.
ASA: American Statistical Association
IEEE/SMC: Institute of Electrical and Electronics Engineers: Systems, Man, and Cybernetics Society
Simio: Simio LLC
ODU: Old Dominion University
ASIM: Arbeitsgemeinschaft Simulation
ExtendSim: ExtendSim
NIST: National Institute of Standards & Technology
Amazon Simulations: Amazon Simulations

Publisher

IEEE Press

Publication History

Published: 11 December 2016

Check for updates

Qualifiers

Research-article

Conference

WSC '16

Sponsor:

IIE
INFORMS-SIM
SIGSIM
SCS

WSC '16: Winter Simulation Conference

December 11 - 14, 2016

Virginia, Arlington

Acceptance Rates

Overall Acceptance Rate 3,413 of 5,075 submissions, 67%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

11
Total Citations
View Citations
91
Total Downloads

Downloads (Last 12 months)5
Downloads (Last 6 weeks)1

Reflects downloads up to 16 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Truger FBarzen JBechtold MBeisel MLeymann FMandl AYussupov V(2024)Warm-Starting and Quantum Computing: A Systematic Mapping StudyACM Computing Surveys10.1145/365251056:9(1-31)Online publication date: 13-Mar-2024
https://dl.acm.org/doi/10.1145/3652510
He LShanbhag USong E(2023)Stochastic Approximation for Multi-period Simulation Optimization with Streaming Input DataACM Transactions on Modeling and Computer Simulation10.1145/3617595Online publication date: 29-Aug-2023
https://dl.acm.org/doi/10.1145/3617595
Chen YSong XLee CWang ZZhang QDohan DKawakami KKochanski GDoucet ARanzato MPerel Sde Freitas NKoyejo SMohamed SAgarwal ABelgrave DCho KOh A(2022)Towards learning universal hyperparameter optimizers with transformersProceedings of the 36th International Conference on Neural Information Processing Systems10.5555/3600270.3602593(32053-32068)Online publication date: 28-Nov-2022
https://dl.acm.org/doi/10.5555/3600270.3602593
Salinas DShen HPerrone VDaumé HSingh A(2020)A quantile-based approach for hyperparameter transfer learningProceedings of the 37th International Conference on Machine Learning10.5555/3524938.3525720(8438-8448)Online publication date: 13-Jul-2020
https://dl.acm.org/doi/10.5555/3524938.3525720
Perrone VShen HSeeger MArchambeau CJenatton RWallach HLarochelle HBeygelzimer Ad'Alché-Buc FFox E(2019)Learning search spaces for Bayesian optimizationProceedings of the 33rd International Conference on Neural Information Processing Systems10.5555/3454287.3455431(12771-12781)Online publication date: 8-Dec-2019
https://dl.acm.org/doi/10.5555/3454287.3455431
Law HZhao PChan LHuang JSejdinovic DWallach HLarochelle HBeygelzimer Ad'Alché-Buc FFox E(2019)Hyperparameter learning via distributional transferProceedings of the 33rd International Conference on Neural Information Processing Systems10.5555/3454287.3454898(6804-6815)Online publication date: 8-Dec-2019
https://dl.acm.org/doi/10.5555/3454287.3454898
Ito HTsutsumida KMatsubayashi TKurashima TToda HSon YHaas P(2019)Coordinated traffic signal control via bayesian optimization for hierarchical conditional spacesProceedings of the Winter Simulation Conference10.5555/3400397.3400693(3645-3656)Online publication date: 8-Dec-2019
https://dl.acm.org/doi/10.5555/3400397.3400693
Perrone VJenatton RSeeger MArchambeau C(2018)Scalable hyperparameter transfer learningProceedings of the 32nd International Conference on Neural Information Processing Systems10.5555/3327757.3327789(6846-6856)Online publication date: 3-Dec-2018
https://dl.acm.org/doi/10.5555/3327757.3327789
Wang ZKim BKaelbling L(2018)Regret bounds for meta Bayesian optimization with an unknown Gaussian process priorProceedings of the 32nd International Conference on Neural Information Processing Systems10.5555/3327546.3327709(10498-10509)Online publication date: 3-Dec-2018
https://dl.acm.org/doi/10.5555/3327546.3327709
Groves MPearce MBranke JJohansson BJain S(2018)On parallelizing multi-task bayesian optimizationProceedings of the 2018 Winter Simulation Conference10.5555/3320516.3320756(1993-2002)Online publication date: 9-Dec-2018
https://dl.acm.org/doi/10.5555/3320516.3320756
Show More Cited By

View Options

Login options

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

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten