Constructing unbiased gradient estimators with finite variance for conditional stochastic optimization

DOI10.1016/j.matcom.2022.09.012OpenAlexW4296984337MaRDI QIDQ2095692

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

stochastic gradient descentmultilevel Monte Carlonested expectationconditional stochastic optimization

Mathematics Subject Classification ID

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

Uses Software

• AdaGrad
• Adam

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Multi-level stochastic approximation algorithms
• Multilevel simulation of functionals of Bernoulli random variables with application to basket credit derivatives
• Monte Carlo complexity of global solution of integral equations
• Bayesian experimental design: A review
• Multilevel particle filters: normalizing constant estimation
• Computing the variance of a conditional expectation via non-nested Monte Carlo
• General multilevel adaptations for stochastic approximation algorithms of Robbins-Monro and Polyak-Ruppert type
• Unbiased estimation of the gradient of the log-likelihood in inverse problems
• Unbiased estimation of the gradient of the log-likelihood for a class of continuous-time state-space models
• First-order and stochastic optimization methods for machine learning
• Nesterov-aided stochastic gradient methods using Laplace approximation for Bayesian design optimization
• Decision-making under uncertainty: using MLMC for efficient estimation of EVPPI
• Antithetic multilevel Monte Carlo estimation for multi-dimensional SDEs without Lévy area simulation
• Unbiased Estimation with Square Root Convergence for SDE Models
• Multilevel Monte Carlo Methods
• Multilevel Monte Carlo estimation of expected information gains
• Multilevel Monte Carlo Path Simulation
• Lectures on Stochastic Programming
• Multilevel Particle Filters
• Unbiased Estimators and Multilevel Monte Carlo
• Unbiased MLMC Stochastic Gradient-Based Optimization of Bayesian Experimental Designs
• Sample Complexity of Sample Average Approximation for Conditional Stochastic Optimization
• Multilevel Monte Carlo Estimation of the Expected Value of Sample Information
• Multilevel Nested Simulation for Efficient Risk Estimation
• A general method for debiasing a Monte Carlo estimator
• A Stochastic Approximation Method

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