Parallelizing exploration-exploitation tradeoffs with Gaussian process bandit optimization

Proceedings of the 29th International Conference on Machine Learning, ICML 2012

Volumn 2, Issue , 2012, Pages 1191-1198

  Desautels, Thomas ^a   Krause, Andreas ^b   Burdick, Joel ^a  

^a CALIFORNIA INSTITUTE OF TECHNOLOGY   (United States)

^b ETH ZURICH   (Switzerland)

Author keywords

[No Author keywords available]

Indexed keywords

BATCH SIZES; CONSTANT FACTORS; GAUSSIAN PROCESS; GAUSSIAN PROCESSES; HIGH-THROUGHPUT; MULTI-ARMED BANDIT PROBLEM; PARALLELIZING; PAYOFF FUNCTION; REAL-WORLD APPLICATION; SEQUENTIAL APPROACH; SURROGATE FUNCTION;

COMMERCE; DESIGN OF EXPERIMENTS; GAUSSIAN DISTRIBUTION; GAUSSIAN NOISE (ELECTRONIC); GLOBAL OPTIMIZATION; LEARNING ALGORITHMS; LEARNING SYSTEMS;

OPTIMIZATION;

EID: 84867115523     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (21)

1. Abernethy, J., Hazan, E., and Rakhlin, A. Competing in the dark: An efficient algorithm for bandit linear optimization. In COLT, 2008.
2. Auer, P., Cesa-Bianchi, N., and Fischer, P. Finite-time analysis of the multiarmed bandit problem. Mach. Learn., 47(2-3):235-256, 2002.
3. Azimi, J., Fern, A., and X.Fern. Batch bayesian optimization via simulation matching. In NIPS, 2010.
4. Brochu, E., Cora, M., and de Freitas, N. A tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning. In TR-2009-23, UBC, 2009.
5. Bubeck, S., Munos, R., Stoltz, G., and Szepesvári, C. Online optimization in X-armed bandits. In NIPS, 2008.
6. Bubeck, S., Munos, R., and Stoltz, G. Pure exploration in multi-armed bandits problems. In ALT, 2009.
7. Cover, T. M. and Thomas, J. A. Elements of Information Theory. Wiley Interscience, 1991.
8. Cox, D. D. and John, S. Sdo: A statistical method for global optimization. Multidisciplinary Design Optimization: State of the Art, 1997.
9. Dani, V., Hayes, T. P., and Kakade, S. M. Stochastic linear optimization under bandit feedback. In COLT, 2008.
10. Dudik, M., Hsu, D., Kale, S., Karampatziakis, N., Langford, J., Reyzin, L., and Zhang, T. Efficient optimal learning for contextual bandits. In UAI, 2011.
11. Ginsbourger, D., Riche, R., and Carraro, L. Kriging is well-suited to parallelize optimization. In Tenne, Yoel and Goh, Chi-Keong (eds.), Computational Intelligence in Expensive Optimization Problems, volume 2 of Adaptation, Learning, and Optimization, pp. 131-162. Springer Berlin Heidelberg, 2010.
12. Jones, D. R., Schonlau, M., and Welch, W. J. Efficient global optimization of expensive black-box functions. J Glob. Opti., 13:455-492, 1998.
13. Kleinberg, R., Slivkins, A., and Upfal, E. Multi-armed bandits in metric spaces. In STOC, pp. 681-690, 2008.
14. Kocsis, L. and Szepesvári, C. Bandit based monte-carlo planning. In ECML, 2006.
15. Lizotte, D., Wang, T., Bowling, M., and Schuurmans, D. Automatic gait optimization with Gaussian process regression. In IJCAI, pp. 944-949, 2007.
16. Minoux, M. Accelerated greedy algorithms for maximizing submodular set functions. Optimization Techniques, LNCS, pp. 234-243, 1978.
17. Mockus, J. Bayesian Approach to Global Optimization. Kluwer Academic Publishers, 1989.
18. Rasmussen, C. E. and Williams, C. K. I. Gaussian Processes for Machine Learning. MIT Press, 2006.
19. Robbins, H. Some aspects of the sequential design of experiments. Bul. Am. Math. Soc., 55, 1952.
20. Srinivas, N., Krause, A., Kakade, S., and Seeger, M. Gaussian process optimization in the bandit setting: No regret and experimental design. In ICML, 2010.
21. Widmer, C., Toussaint, N., Altun, Y., and Rätsch, G. Inferring latent task structure for multitask learning by multiple kernel learning. BMG Bioinformatics, 11(Suppl 8:S5), 2010.