Abstract
We consider the problem of online stratified sampling for Monte Carlo integration of a function given a finite budget of n noisy evaluations to the function. More precisely we focus on the problem of choosing the number of strata K as a function of the numerical budget n. We provide asymptotic and finite-time results on how an oracle that knows the smoothness of the function would choose the number of strata optimally. In addition we prove a lower bound on the learning rate for the problem of stratified Monte-Carlo. As a result, we are able to state, by improving the bound on its performance, that algorithm MC-UCB, defined in [1, is minimax optimal both in terms of the number of samples n and the number of strata K, up to a log factor. This enables to deduce a minimax optimal bound on the difference between the performance of the estimate output by MC-UCB, and the performance of the estimate output by the best oracle static strategy, on the class of Hölder continuous functions, and up to a log factor.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Carpentier, A., Munos, R.: Finite-time analysis of stratified sampling for monte carlo. In: Neural Information Processing Systems, NIPS (2011a)
Carpentier, A., Munos, R.: Finite-time analysis of stratified sampling for monte carlo. Technical report, INRIA-00636924 (2011b)
Etoré, P., Jourdain, B.: Adaptive optimal allocation in stratified sampling methods. Methodol. Comput. Appl. Probab. 12(3), 335–360 (2010)
Etoré, P., Fort, G., Jourdain, B., Moulines, É.: On adaptive stratification. Ann. Oper. Res. (2011) (to appear)
Giné, E., Nickl, R.: Confidence bands in density estimation. The Annals of Statistics 38(2), 1122–1170 (2010)
Glasserman, P.: Monte Carlo methods in financial engineering. Springer (2004) ISBN 0387004513
Glasserman, P., Heidelberger, P., Shahabuddin, P.: Asymptotically optimal importance sampling and stratification for pricing path-dependent options. Mathematical Finance 9(2), 117–152 (1999)
Grover, V.: Active learning and its application to heteroscedastic problems. Department of Computing Science, Univ. of Alberta, MSc thesis (2009)
Hoffmann, M., Lepski, O.: Random rates in anisotropic regression. Annals of Statistics, 325–358 (2002)
Kawai, R.: Asymptotically optimal allocation of stratified sampling with adaptive variance reduction by strata. ACM Transactions on Modeling and Computer Simulation (TOMACS) 20(2), 1–17 (2010) ISSN 1049-3301
Rubinstein, R.Y., Kroese, D.P.: Simulation and the Monte Carlo method. Wiley-interscience (2008) ISBN 0470177942
Carpentier, A., Munos, R.: Minimax Number of Strata for Online Stratified Sampling given Noisy Samples. Technical report, INRIA-00698517 (2012)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Carpentier, A., Munos, R. (2012). Minimax Number of Strata for Online Stratified Sampling Given Noisy Samples. In: Bshouty, N.H., Stoltz, G., Vayatis, N., Zeugmann, T. (eds) Algorithmic Learning Theory. ALT 2012. Lecture Notes in Computer Science(), vol 7568. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-34106-9_20
Download citation
DOI: https://doi.org/10.1007/978-3-642-34106-9_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-34105-2
Online ISBN: 978-3-642-34106-9
eBook Packages: Computer ScienceComputer Science (R0)