English
Related papers

Related papers: Modeling the Second Player in Distributionally Rob…

200 papers

Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), as the widely employed policy based reinforcement learning (RL) methods, are prone to converge to a sub-optimal solution as they limit the policy representation…

Machine Learning · Computer Science 2020-06-16 Jun Song , Chaoyue Zhao

Predict-then-Optimize (PTO) pipelines are widely employed in computing and networked systems, where Machine Learning (ML) models are used to predict critical contextual information for downstream decision-making tasks such as cloud LLM…

Machine Learning · Computer Science 2026-02-04 Jiaqi Wen , Lei Fan , Jianyi Yang

This paper studies Markov Decision Processes under parameter uncertainty. We adapt the distributionally robust optimization framework, and assume that the uncertain parameters are random variables following an unknown distribution, and…

Systems and Control · Computer Science 2015-05-14 Pengqian Yu , Huan Xu

Robust and distributionally robust optimization are modeling paradigms for decision-making under uncertainty where the uncertain parameters are only known to reside in an uncertainty set or are governed by any probability distribution from…

Optimization and Control · Mathematics 2023-07-21 Jianzhe Zhen , Daniel Kuhn , Wolfram Wiesemann

The Robust Markov Decision Process (RMDP) framework focuses on designing control policies that are robust against the parameter uncertainties due to the mismatches between the simulator model and real-world settings. An RMDP problem is…

Machine Learning · Computer Science 2022-05-17 Kishan Panaganti , Dileep Kalathil

Modern neural networks are able to perform at least as well as humans in numerous tasks involving object classification and image generation. However, small perturbations which are imperceptible to humans may significantly degrade the…

Computer Vision and Pattern Recognition · Computer Science 2021-12-01 Xinru Hua , Huanzhong Xu , Jose Blanchet , Viet Nguyen

We study finite-sample statistical performance guarantees for distributionally robust optimization (DRO) with optimal transport (OT) and OT-regularized divergence model neighborhoods. Specifically, we derive concentration inequalities for…

Machine Learning · Statistics 2026-03-31 Jeremiah Birrell , Xiaoxi Shen

The goal of robust constrained reinforcement learning (RL) is to optimize an agent's performance under the worst-case model uncertainty while satisfying safety or resource constraints. In this paper, we demonstrate that strong duality does…

Machine Learning · Computer Science 2025-09-23 Shaocong Ma , Ziyi Chen , Yi Zhou , Heng Huang

When training and evaluating machine learning models on a large number of tasks, it is important to not only look at average task accuracy -- which may be biased by easy or redundant tasks -- but also worst-case accuracy (i.e. the…

Machine Learning · Computer Science 2021-10-13 Paul Michel , Sebastian Ruder , Dani Yogatama

Conventional supervised learning methods are often vulnerable to spurious correlations, particularly under distribution shifts in test data. To address this issue, several approaches, most notably Group DRO, have been developed. While these…

Machine Learning · Computer Science 2026-02-13 Sung Ho Jo , Seonghwi Kim , Minwoo Chae

Constrained reinforcement learning is to maximize the expected reward subject to constraints on utilities/costs. However, the training environment may not be the same as the test one, due to, e.g., modeling error, adversarial attack,…

Machine Learning · Computer Science 2022-09-16 Yue Wang , Fei Miao , Shaofeng Zou

The study of robustness has received much attention due to its inevitability in data-driven settings where many systems face uncertainty. One such example of concern is Bayesian Optimization (BO), where uncertainty is multi-faceted, yet…

Machine Learning · Computer Science 2023-10-31 Hisham Husain , Vu Nguyen , Anton van den Hengel

Wasserstein distributionally robust optimization (WDRO) attempts to learn a model that minimizes the local worst-case risk in the vicinity of the empirical data distribution defined by Wasserstein ball. While WDRO has received attention as…

Machine Learning · Statistics 2020-06-23 Yongchan Kwon , Wonyoung Kim , Joong-Ho Won , Myunghee Cho Paik

Reinforcement learning (RL) policies often fail under dynamics that differ from training, a gap not fully addressed by domain randomization or existing adversarial RL methods. Distributionally robust RL provides a formal remedy but still…

Machine Learning · Computer Science 2026-04-16 Mintae Kim , Koushil Sreenath

Despite the high performance achieved by deep neural networks on various tasks, extensive studies have demonstrated that small tweaks in the input could fail the model predictions. This issue of deep neural networks has led to a number of…

Machine Learning · Computer Science 2022-02-22 Ming-Chang Chiu , Xuezhe Ma

We introduce a new framework, Bayesian Distributionally Robust Optimization (Bayesian-DRO), for data-driven stochastic optimization where the underlying distribution is unknown. Bayesian-DRO contrasts with most of the existing DRO…

Optimization and Control · Mathematics 2023-02-10 Alexander Shapiro , Enlu Zhou , Yifan Lin

Predictive models for clinical outcomes that are accurate on average in a patient population may underperform drastically for some subpopulations, potentially introducing or reinforcing inequities in care access and quality. Model training…

Machine Learning · Statistics 2022-02-03 Stephen R. Pfohl , Haoran Zhang , Yizhe Xu , Agata Foryciarz , Marzyeh Ghassemi , Nigam H. Shah

Distributionally Robust Optimization (DRO) has been shown to provide a flexible framework for decision making under uncertainty and statistical estimation. For example, recent works in DRO have shown that popular statistical estimators can…

Machine Learning · Statistics 2020-04-21 Jose Blanchet , Yang Kang , Fan Zhang , Zhangyi Hu

We consider stochastic programs conditional on some covariate information, where the only knowledge of the possible relationship between the uncertain parameters and the covariates is reduced to a finite data sample of their joint…

Optimization and Control · Mathematics 2021-11-23 Adrián Esteban-Pérez , Juan M. Morales

Wasserstein distributionally robust optimization (WDRO) optimizes against worst-case distributional shifts within a specified uncertainty set, leading to enhanced generalization on unseen adversarial examples, compared to standard…

Machine Learning · Computer Science 2025-03-07 Shuang Liu , Yihan Wang , Yifan Zhu , Yibo Miao , Xiao-Shan Gao