Empirical variance minimization with applications in variance reduction and optimal control

DOI10.3150/21-BEJ1392MaRDI QIDQ2137023

Leonid Iosipoi, Quentin Paris, Nikita Zhivotovskiy, Denis Belomestny

Publication date: 16 May 2022

Published in: Bernoulli (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1712.04667

zbMATH Keywords

optimal controlvariance reductioncontrol variatesempirical variance minimization

Mathematics Subject Classification ID

Multivariate analysis (62Hxx) Stochastic processes (60Gxx) Nonparametric inference (62Gxx)

Related Items

Empirical variance minimization with applications in variance reduction and optimal control

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Zero variance Markov chain Monte Carlo for Bayesian estimators
• Robust estimation of \(U\)-statistics
• A statistical view of clustering performance through the theory of \(U\)-processes
• General nonexact oracle inequalities for classes with a subexponential envelope
• Empirical entropy, minimax regret and minimax risk
• Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
• Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
• Risk bounds for model selection via penalization
• Rates of convergence for minimum contrast estimators
• Information-theoretic determination of minimax rates of convergence
• Variance reduction in Monte Carlo estimators via empirical variance minimization
• Probability inequalities for likelihood ratios and convergence rates of sieve MLEs
• Weak convergence and empirical processes. With applications to statistics
• Empirical variance minimization with applications in variance reduction and optimal control
• Variance reduction for Markov chains with application to MCMC
• Isotonic regression in general dimensions
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• Ranking and empirical minimization of \(U\)-statistics
• Empirical minimization
• Local Rademacher complexities
• Bracketing metric entropy rates and empirical central limit theorems for function classes of Besov- and Sobolev-type
• Concentration Inequalities
• Pathwise Stochastic Optimal Control
• Advanced Simulation-Based Methods for Optimal Stopping and Control
• High-Dimensional Statistics
• Variance Reduction for Dependent Sequences with Applications to Stochastic Gradient MCMC
• Probability Inequalities for Sums of Bounded Random Variables
• Control Functionals for Monte Carlo Integration
• A Class of Statistics with Asymptotically Normal Distribution
• The Theory of Unbiased Estimation