Constructing unbiased gradient estimators with finite variance for conditional stochastic optimization

DOI10.1016/J.MATCOM.2022.09.012MaRDI QIDQ2095692zbMATH OpenOpenAlexFDO

Authors Takashi Goda, Wataru Kitade

Publication date 17 November 2022

Published in Mathematics and Computers in Simulation (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2206.01991

zbMATH Keywords

conditional stochastic optimizationmultilevel Monte Carlonested expectationstochastic gradient descent

Mathematics Subject Classification ID

Probability theory and stochastic processes (60-XX) Statistics (62-XX)

Recommendations

• Computing the variance of a conditional expectation via non-nested Monte Carlo
• Unbiased MLMC stochastic gradient-based optimization of Bayesian experimental designs
• scientific article; zbMATH DE number 912592
• scientific article; zbMATH DE number 1002915
• On the variance of single-run unbiased stochastic derivative estimators

Cites work

• A general method for debiasing a Monte Carlo estimator
• A Stochastic Approximation Method
• Adaptive subgradient methods for online learning and stochastic optimization
• Antithetic multilevel Monte Carlo estimation for multi-dimensional SDEs without Lévy area simulation
• Bayesian experimental design: A review
• Computing the variance of a conditional expectation via non-nested Monte Carlo
• Decision-making under uncertainty: using MLMC for efficient estimation of EVPPI
• First-order and stochastic optimization methods for machine learning
• General multilevel adaptations for stochastic approximation algorithms of Robbins-Monro and Polyak-Ruppert type
• scientific article; zbMATH DE number 3850830 (Why is no real title available?)
• scientific article; zbMATH DE number 51379 (Why is no real title available?)
• scientific article; zbMATH DE number 1972910 (Why is no real title available?)
• scientific article; zbMATH DE number 2106098 (Why is no real title available?)
• Lectures on Stochastic Programming
• Monte Carlo complexity of global solution of integral equations
• Multi-level stochastic approximation algorithms
• Multilevel Monte Carlo estimation of expected information gains
• Multilevel Monte Carlo estimation of the expected value of sample information
• Multilevel Monte Carlo Path Simulation
• Multilevel nested simulation for efficient risk estimation
• Multilevel Particle Filters
• Multilevel particle filters: normalizing constant estimation
• Multilevel simulation of functionals of Bernoulli random variables with application to basket credit derivatives
• Nesterov-aided stochastic gradient methods using Laplace approximation for Bayesian design optimization
• Sample complexity of sample average approximation for conditional stochastic optimization
• Unbiased estimation of the gradient of the log-likelihood for a class of continuous-time state-space models
• Unbiased estimation of the gradient of the log-likelihood in inverse problems
• Unbiased estimation with square root convergence for SDE models
• Unbiased estimators and multilevel Monte Carlo
• Unbiased MLMC stochastic gradient-based optimization of Bayesian experimental designs

Cited in

(6)

• On the variance of single-run unbiased stochastic derivative estimators
• scientific article; zbMATH DE number 7625177 (Why is no real title available?)
• Enhanced Balancing of Bias-Variance Tradeoff in Stochastic Estimation: A Minimax Perspective
• Constructing unbiased gradient estimators with finite variance for conditional stochastic optimization
• A functional model method for nonconvex nonsmooth conditional stochastic optimization
• Deep learning for Markov chains: Lyapunov functions, Poisson's equation, and stationary distributions

Describes a project that uses

Uses Software

• Adam
• AdaGrad

This page was built for publication: Constructing unbiased gradient estimators with finite variance for conditional stochastic optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2095692)