Unbiased Multilevel Monte Carlo: Stochastic Optimization, Steady-state Simulation, Quantiles, and Other Applications

Abstract

We present general principles for the design and analysis of unbiased Monte Carlo estimators in a wide range of settings. Our estimators posses finite work-normalized variance under mild regularity conditions. We apply our estimators to various settings of interest, including unbiased optimization in Sample Average Approximations, unbiased steady-state simulation of regenerative processes, quantile estimation and nested simulation problems.

arXiv comment20 pages, 2 figures

References in corpus (1)

• General multilevel adaptations for stochastic approximation algorithms

Cited by in corpus (3)

• Machine Learning's Dropout Training is Distributionally Robust Optimal
• Optimal unbiased estimators via convex hulls
• Unbiased Optimal Stopping via the MUSE