paper-with-me

홈 › Papers

Contextual Optimization under Covariate Shift: A Robust Approach by Intersecting Wasserstein Balls

2024-06-04 · Tianyu Wang, Ningyuan Chen, Chun Wang

In contextual optimization, a decision-maker leverages contextual information, often referred to as covariates, to better resolve uncertainty and make informed decisions. In this paper, we examine the challenges of contextual decision-making under covariate shift, a phenomenon where the distribution of covariates differs between the training and test environments. Such shifts can lead to inaccurate upstream estimations for test covariates that lie far from the training data, ultimately resulting in suboptimal downstream decisions. To tackle these challenges, we propose a novel approach called Intersection Wasserstein-balls DRO (IW-DRO), which integrates multiple estimation methods into the distributionally robust optimization (DRO) framework. At the core of our approach is an innovative ambiguity set defined as the intersection of two Wasserstein balls, with their centers constructed using appropriate nonparametric and parametric estimators. On the computational side, we reformulate the IW-DRO problem as a tractable convex program and develop an approximate algorithm tailored for large-scale problems to enhance computational efficiency. From a theoretical perspective, we demonstrate that IW-DRO achieves superior performance compared to single Wasserstein-ball DRO models. We further establish performance guarantees by analyzing the coverage of the intersection ambiguity set and the measure concentration of both estimators under the Wasserstein distance. Notably, we derive a finite-sample concentration result for the Nadaraya-Watson kernel estimator under covariate shift. The proposed IW-DRO framework offers practical value for decision-makers operating in uncertain environments affected by covariate shifts.

📄 PDF Abstract BibTeX arXiv:2406.02426

Code (0)

등록된 구현이 없습니다.

Tasks

Computational EfficiencyPortfolio Optimization

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

PAC Learning Guarantees Under Covariate Shift

2018-12-16 · Artidoro Pagnoni, Stefan Gramatovici, Samuel Liu

We consider the Domain Adaptation problem, also known as the covariate shift problem, where the distributions that generate the training and test data differ while retaining the same labeling function. This problem occur…

Domain AdaptationPAC learningTransfer Learning

Distributionally Robust Policy Evaluation under General Covariate Shift in Contextual Bandits

2024-01-21 · Yihong Guo, Hao liu, Yisong Yue, Anqi Liu

We introduce a distributionally robust approach that enhances the reliability of offline policy evaluation in contextual bandits under general covariate shifts. Our method aims to deliver robust policy evaluation results…

Multi-Armed Banditsregression

Self-Tuning Bandits over Unknown Covariate-Shifts

2020-07-16 · Joseph Suk, Samory Kpotufe

Bandits with covariates, a.k.a. contextual bandits, address situations where optimal actions (or arms) at a given time $t$, depend on a context $x_t$, e.g., a new patient's medical history, a consumer's past purchases. W…

Multi-Armed Bandits

Bridging Multicalibration and Out-of-distribution Generalization Beyond Covariate Shift

2024-06-02 · Jiayun Wu, Jiashuo Liu, Peng Cui, Zhiwei Steven Wu

We establish a new model-agnostic optimization framework for out-of-distribution generalization via multicalibration, a criterion that ensures a predictor is calibrated across a family of overlapping groups. Multicalibra…

Out-of-Distribution Generalization

On Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning

2021-10-13 · ICLR 2022 4 · Guy Tennenholtz, Assaf Hallak, Gal Dalal, Shie Mannor 외

We consider the problem of using expert data with unobserved confounders for imitation and reinforcement learning. We begin by defining the problem of learning from confounded expert data in a contextual MDP setup. We an…

Imitation LearningRecommendation Systemsreinforcement-learningReinforcement Learning (RL)