The Square Root Rule for Adaptive Importance Sampling
Authors: 
Art B. Owen, Yi ZhouAuthors Info & Claims
Art B. Owen, Yi ZhouAuthors Info & ClaimsArticle No.: 13, Pages 1 - 12
Abstract
In adaptive importance sampling and other contexts, we have K > 1 unbiased and uncorrelated estimates μ^k of a common quantity μ. The optimal unbiased linear combination weights them inversely to their variances, but those weights are unknown and hard to estimate. A simple deterministic square root rule based on a working model that Var(μ^k) ∝ k−1/2 gives an unbiased estimate of μ that is nearly optimal under a wide range of alternative variance patterns. We show that if Var(μ^k)∝ k−y for an unknown rate parameter y∈[0,1], then the square root rule yields the optimal variance rate with a constant that is too large by at most 9/8 for any 0 ⩽ y⩽ 1 and any number K of estimates. Numerical work shows that rule is similarly robust to some other patterns with mildly decreasing variance as k increases.
References
[1]
Siu-Kui Au and James L. Beck. 1999. A new adaptive importance sampling scheme for reliability calculations. Structural Safety 21, 2 (1999), 135--158.
[2]
José Blanchet, Peter Glynn, and Jingchen C. Liu. 2007. Fluid heuristics, Lyapunov bounds and efficient importance sampling for a heavy-tailed G/G/1 queue. Queueing Systems 57, 2--3 (2007), 99--113.
[3]
Brian L. Burrows and Richard F. Talbot. 1984. Sums of powers of integers. The American Mathematical Monthly 91, 7 (1984), 394--403.
[4]
Sourav Chatterjee and Persi Diaconis. 2018. The sample size required in importance sampling. The Annals of Applied Probability 28, 2 (2018), 1099--1135.
[5]
Jean-Marie Cornuet, Jean-Michel Marin, Antonietta Mira, and Christian P. Robert. 2012. Adaptive multiple importance sampling. Scandinavian Journal of Statistics 39, 4 (2012), 798--812.
[6]
Pieter-Tjerk De Boer, Dirk P. Kroese, Shie. Mannor, and Reuven Y. Rubinstein. 2005. A tutorial on the cross-entropy method. Annals of Operations Research 134, 1 (2005), 19--67.
[7]
Victor Elvira and Ignacio Santamaria. 2019. Multiple importance sampling for efficient symbol error rate estimation. IEEE Signal Processing Letters 26, 3 (2019), 420--424.
[8]
Michael J. Evans and Tim Swartz. 1995. Methods for approximating integrals in statistics with special emphasis on Bayesian integration problems. Statist. Sci. 10, 3 (1995), 254--272.
[9]
Paul G. Glasserman. 2004. Monte Carlo Methods in Financial Engineering. Springer, New York.
[10]
Timothy C. Hesterberg. 1988. Advances in Importance Sampling. Ph.D. Dissertation. Stanford University.
[11]
Herman Kahn and Andrew Marshall. 1953. Methods of reducing sample size in monte carlo computations. Journal of the Operations Research Society of America 1, 5 (1953), 263--278.
[12]
Craig Kollman, Keith Baggerly, Dennis Cox, and Rick Picard. 1999. Adaptive importance sampling on discrete Markov chains. Annals of Applied Probability 9, 2 (1999), 391--412.
[13]
Rong Kong and Jerome Spanier. 2011. Geometric convergence of adaptive monte carlo algorithms for radiative transport problems based on importance sampling methods. Nuclear Science and Engineering 168, 3 (2011), 197--225.
[14]
Tze L. Lai and David Siegmund. 1977. A nonlinear renewal theory with applications to sequential analysis I. The Annals of Statistics 5, 5 (1977), 946--954.
[15]
Pierre. L’Ecuyer, José. H. Blanchet, Bruno. Tuffin, and Peter W. Glynn. 2010. Asymptotic robustness of estimators in rare-event simulation. ACM Transactions on Modeling and Computer Simulation (TOMACS) 20, 1 (2010), 6.
[16]
Pierre L’Ecuyer and Christian Lemieux. 2000. Variance reduction via lattice rules. Management Science 46, 9 (2000), 1214--1235.
[17]
Pierre L’Ecuyer, Michel Mandjes, and Bruno Tuffin. 2009. Importance sampling and rare event simulation. In Rare Event Simulation Using Monte Carlo Methods, G. Rubino and B. Tuffin (Eds.). John Wiley 8 Sons, Chichester, UK, 17--38.
[18]
Pierre L’Ecuyer and Bruno Tuffin. 2008. Approximate zero-variance simulation. In Proceedings of the 2008 Winter Simulation Conference, S. J. Mason, R. R. Hill, L. Mönch, O. Rose, T. Jefferson, and J. W. Fowler (Eds.). IEEE Press, 170--181.
[19]
Rupert G. Miller. 1986. Beyond ANOVA: Basics of Applied Statistics. Wiley, New York.
[20]
Art B. Owen. 1997. Scrambled net variance for integrals of smooth functions. Annals of Statistics 25, 4 (1997), 1541--1562.
[21]
Art B. Owen, Yury Maximov, and Michael Chertkov. 2019. Importance sampling the union of rare events with an application to power systems analysis. Electronic Journal of Statistics 13, 1 (2019), 231--254.
[22]
Art B. Owen and Y. Zhou. 1999. Adaptive Importance Sampling by Mixtures of Products of Beta Distributions. Technical Report. Stanford University.
[23]
Matt Pharr, Wenzel Jakob, and Greg Humphreys. 2016. Physically Based Rendering: From Theory to Implementation (third ed.). Morgan Kaufmann, Cambridge, MA.
[24]
Ernest K. Ryu and Stephen P. Boyd. 2014. Adaptive Importance Sampling via Stochastic Convex Programming. Technical Report. arXiv:1412.4845.
[25]
Eric Veach and Leonidas Guibas. 1995. Optimally combining sampling techniques for monte carlo rendering. In SIGGRAPH’95 Conference Proceedings. Addison-Wesley, Reading, MA, 419--428.
[26]
Mike West. 1993. Approximating posterior distributions by mixtures. Journal of the Royal Statistical Society: Series B 55, 2 (1993), 409--422.
[27]
David Williams. 1991. Probability with Martingales. Cambridge University Press, Cambridge.
[28]
Ping Zhang. 1996. Nonparametric importance sampling. J. Amer. Statist. Assoc. 91, 435 (1996), 1245--1253.
Index Terms
- The Square Root Rule for Adaptive Importance Sampling
Recommendations
A Non-Data-Aided Maximum Likelihood Time Delay Estimator Using Importance Sampling
In this paper, we present a new time delay maximum likelihood estimator based on importance sampling (IS). We show that a grid search and lack of convergence from which most iterative estimators suffer can be avoided. It is assumed that the transmitted ...
Analysis of an importance sampling estimator for tandem queues
We analyze the performance of an importance sampling estimator for a rare-event probability in tandem Jackson networks. The rare event we consider corresponds to the network population reaching K before returning to ø, starting from ø, with K large. The ...
Importance sampling for sums of random variables with regularly varying tails
Importance sampling is a variance reduction technique for efficient estimation of rare-event probabilities by Monte Carlo. For random variables with heavy tails there is little consensus on how to choose the change of measure used in importance ...
Comments
Information & Contributors
Information
Published In
April 2020
118 pages
Copyright © 2020 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 20 March 2020
Accepted: 01 July 2019
Revised: 01 June 2019
Received: 01 January 2019
Published in TOMACS Volume 30, Issue 2
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed
Funding Sources
- U.S. National Science Foundation
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 206Total Downloads
- Downloads (Last 12 months)22
- Downloads (Last 6 weeks)1
Reflects downloads up to 11 Aug 2024
Other Metrics
Citations
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.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format