Saved in:
Bibliographic Details
Main Authors: Şen, Buse, Hu, Yifan, Kuhn, Daniel
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.14075
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918448930488320
author Şen, Buse
Hu, Yifan
Kuhn, Daniel
author_facet Şen, Buse
Hu, Yifan
Kuhn, Daniel
contents We introduce Multistage Conditional Compositional Optimization (MCCO) as a new paradigm for decision-making under uncertainty that combines aspects of multistage stochastic programming and conditional stochastic optimization. MCCO minimizes a nest of conditional expectations and nonlinear cost functions. It has numerous applications and arises, for example, in optimal stopping, linear-quadratic regulator problems, distributionally robust contextual bandits, as well as in problems involving dynamic risk measures. The naïve nested sampling approach for MCCO suffers from the curse of dimensionality familiar from scenario tree-based multistage stochastic programming, that is, its scenario complexity grows exponentially with the number of nests. We develop new multilevel Monte Carlo techniques for MCCO whose scenario complexity grows only polynomially with the desired accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2604_14075
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Multistage Conditional Compositional Optimization
Şen, Buse
Hu, Yifan
Kuhn, Daniel
Optimization and Control
Machine Learning
We introduce Multistage Conditional Compositional Optimization (MCCO) as a new paradigm for decision-making under uncertainty that combines aspects of multistage stochastic programming and conditional stochastic optimization. MCCO minimizes a nest of conditional expectations and nonlinear cost functions. It has numerous applications and arises, for example, in optimal stopping, linear-quadratic regulator problems, distributionally robust contextual bandits, as well as in problems involving dynamic risk measures. The naïve nested sampling approach for MCCO suffers from the curse of dimensionality familiar from scenario tree-based multistage stochastic programming, that is, its scenario complexity grows exponentially with the number of nests. We develop new multilevel Monte Carlo techniques for MCCO whose scenario complexity grows only polynomially with the desired accuracy.
title Multistage Conditional Compositional Optimization
topic Optimization and Control
Machine Learning
url https://arxiv.org/abs/2604.14075