paper-with-me

Papers

Distributionally Robust Policy Learning under Concept Drifts

2024-12-18 · Jingyuan Wang, Zhimei Ren, Ruohan Zhan, Zhengyuan Zhou

Distributionally robust policy learning aims to find a policy that performs well under the worst-case distributional shift, and yet most existing methods for robust policy learning consider the worst-case joint distribution of the covariate and the outcome. The joint-modeling strategy can be unnecessarily conservative when we have more information on the source of distributional shifts. This paper studiesa more nuanced problem -- robust policy learning under the concept drift, when only the conditional relationship between the outcome and the covariate changes. To this end, we first provide a doubly-robust estimator for evaluating the worst-case average reward of a given policy under a set of perturbed conditional distributions. We show that the policy value estimator enjoys asymptotic normality even if the nuisance parameters are estimated with a slower-than-root-$n$ rate. We then propose a learning algorithm that outputs the policy maximizing the estimated policy value within a given policy class $\Pi$, and show that the sub-optimality gap of the proposed algorithm is of the order $\kappa(\Pi)n^{-1/2}$, with $\kappa(\Pi)$ is the entropy integral of $\Pi$ under the Hamming distance and $n$ is the sample size. A matching lower bound is provided to show the optimality of the rate. The proposed methods are implemented and evaluated in numerical studies, demonstrating substantial improvement compared with existing benchmarks.

📄 PDF Abstract BibTeX arXiv:2412.14297

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

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

Similar Papers 제목 키워드 기반

DriftGAN: Using historical data for Unsupervised Recurring Drift Detection

2024-07-09 · Christofer Fellicious, Sahib Julka, Lorenz Wendlinger, Michael Granitzer

In real-world applications, input data distributions are rarely static over a period of time, a phenomenon known as concept drift. Such concept drifts degrade the model's prediction performance, and therefore we require …

Drift Detection

Tackling Virtual and Real Concept Drifts: An Adaptive Gaussian Mixture Model

2021-02-11 · Gustavo Oliveira, Leandro Minku, Adriano Oliveira

Real-world applications have been dealing with large amounts of data that arrive over time and generally present changes in their underlying joint probability distribution, i.e., concept drift. Concept drift can be subdi…

Distributionally Robust Control Synthesis for Stochastic Systems with Safety and Reach-Avoid Specifications

2025-01-06 · Yu Chen, Yuda Li, ShaoYuan Li, Xiang Yin

We investigate the problem of synthesizing distributionally robust control policies for stochastic systems under safety and reach-avoid specifications. Using a game-theoretical framework, we consider the setting where th…

DriftSurf: A Risk-competitive Learning Algorithm under Concept Drift

2020-03-13 · Ashraf Tahmasbi, Ellango Jothimurugesan, Srikanta Tirthapura, Phillip B. Gibbons

When learning from streaming data, a change in the data distribution, also known as concept drift, can render a previously-learned model inaccurate and require training a new model. We present an adaptive learning algori…

Drift Detection

Federated Learning under Distributed Concept Drift

2022-06-01 · Ellango Jothimurugesan, Kevin Hsieh, Jianyu Wang, Gauri Joshi 외

Federated Learning (FL) under distributed concept drift is a largely unexplored area. Although concept drift is itself a well-studied phenomenon, it poses particular challenges for FL, because drifts arise staggered in t…

ClusteringDrift DetectionFederated Learning