Contextual Learning for Stochastic Optimization
Motivated by stochastic optimization, we introduce the problem of learning from samples of contextual value distributions. A contextual value distribution can be understood as a family of real-valued distributions, where each sample consists of a context $x$ and a random variable drawn from the corresponding real-valued distribution $D_x$. By minimizing a convex surrogate loss, we learn an empirical distribution $D'_x$ for each context, ensuring a small L\'evy distance to $D_x$. We apply this result to obtain the sample complexity bounds for the learning of an $\epsilon$-optimal policy for stochastic optimization problems defined on an unknown contextual value distribution. The sample complexity is shown to be polynomial for the general case of strongly monotone and stable optimization problems, including Single-item Revenue Maximization, Pandora's Box and Optimal Stopping.
Code (0)
등록된 구현이 없습니다.
Tasks
Stochastic OptimizationSimilar Papers 제목 키워드 기반
Contextual Stochastic Bilevel Optimization
We introduce contextual stochastic bilevel optimization (CSBO) -- a stochastic bilevel optimization framework with the lower-level problem minimizing an expectation conditioned on some contextual information and the uppe…
Bilevel OptimizationFederated LearningMeta-LearningPersonalized Federated LearningHeteroscedasticity-aware residuals-based contextual stochastic optimization
We explore generalizations of some integrated learning and optimization frameworks for data-driven contextual stochastic optimization that can adapt to heteroscedasticity. We identify conditions on the stochastic program…
regressionStochastic OptimizationPrimal-dual algorithm for contextual stochastic combinatorial optimization
This paper introduces a novel approach to contextual stochastic optimization, integrating operations research and machine learning to address decision-making under uncertainty. Traditional methods often fail to leverage …
Combinatorial OptimizationDecision Making Under UncertaintyImitation LearningStochastic OptimizationStatistical Inference for Weighted Sample Average Approximation in Contextual Stochastic Optimization
Contextual stochastic optimization provides a framework for decision-making under uncertainty incorporating observable contextual information through covariates. We analyze statistical inference for weighted sample avera…
Decision MakingDecision Making Under UncertaintyStochastic OptimizationvalidEvaluation of Prosumer Networks for Peak Load Management in Iran: A Distributed Contextual Stochastic Optimization Approach
Renewable prosumers face the complex challenge of balancing self-sufficiency with seamless grid and market integration. This paper introduces a novel prosumers network framework aimed at mitigating peak loads in Iran, pa…
ManagementStochastic Optimization