Distributionally Robust Optimization

Follow this topic Ask about this topic

DRO studies how to make predictions and decisions reliable when the distribution at deployment may differ from the observed data. Methods define ambiguity sets using tools such as Wasserstein distance, statistical divergences, or group-based reweighting, then solve the resulting worst-case optimization with dual formulations, gradient methods, or saddle-point algorithms. Applications include machine learning under subgroup and domain shifts, reinforcement learning, control, and decisions in areas such as healthcare and energy. A central challenge is balancing protection against distribution shift with computational cost and excessive conservatism, while choosing ambiguity sets that reflect real uncertainty and still support useful guarantees.

Latest papers

86 papers18 papers in the last four weeks, up 350% on the four weeks before. 0.1% of all new papers.

Stein Variational Uncertainty-Adaptive Model Predictive Control
Apr 1, 2026Hrishikesh Sathyanarayan, Ian AbrahamModel Predictive Control Nonlinear MPC
Department of Mechanical Engineering, Yale University, USA · Department of Electrical Engineering, University of Sydney, Australia
Statistical Guarantees for Distributionally Robust Optimization with Optimal Transport and OT-Regularized Divergences
Mar 29, 2026Jeremiah Birrell, Xiaoxi ShenDistributionally Robust Optimization Wasserstein Distributionally Robust Optimization
Department of Mathematics Texas State University San Marcos, TX, USA
Maximin Learning of Individualized Treatment Effect on Multi-Domain Outcomes
Mar 28, 2026Yuying Lu, Wenbo Fei, Yuanjia Wang +1Individualized Treatment Effect Estimation Causal Effect Estimation
Department of Biostatistics, Columbia Mailman School of Public Health. · Department of Biostatistics, Peking University Health Science Center. · Beijing International Center for Mathematical Research, Peking University.
Distributionally Robust Token Optimization in RLHF
Mar 27, 2026Yeping Jin, Jiaming Hu, Ioannis Ch. PaschalidisLanguage Model Robustness Reasoning Consistency in Language Models
Department of System Engineering Boston University, Boston, MA 02215, USA · Department of Math & Statistics Boston University, Boston, MA 02215, USA
Safe Distributionally Robust Feature Selection under Covariate Shift
Mar 17, 2026Hiroyuki Hanada, Satoshi Akahane, Noriaki Hashimoto +2Feature Selection Distributionally Robust Optimization
Graduate School of Engineering, Nagoya University, Nagoya, Japan · Center for Advanced Intelligence Project, RIKEN, Tokyo, Japan
Towards Fair and Robust Volumetric CT Classification via KL-Regularised Group Distributionally Robust Optimisation
Mar 16, 2026Samuel Johnny, Blessed Guda, Goodness Obasi +2Group Distributionally Robust Optimization Medical Image Classification
Carnegie Mellon University Africa, Kigali, Rwanda · Carnegie Mellon University, Pittsburgh, USA
Worst-case low-rank approximations
Mar 11, 2026Anya Fries, Markus Reichstein, David Blei +1Low-Rank Approximation Distribution Shift Robustness
Seminar for Statistics, ETH Zürich, Zürich, Switzerland · Max Planck Institute for Biogeochemistry, Jena, Germany · Department of Computer Science and Department of Statistics, Columbia University, New York, USA
Data-driven robust Markov decision processes on Borel spaces: performance guarantees via an axiomatic approach
Mar 9, 2026Sivaramakrishnan RamaniRobust Markov Decision Processes Distributionally Robust Optimization
Department of Computational Applied Mathematics and Operations Research, Rice University, Houston, USA.
DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding
Mar 9, 2026Mingxi Zou, Jiaxiang Chen, Junfan Li +4Preference Alignment Inference-Time Language Model Alignment
Fudan University, Shanghai, China · Independent Researcher · Meta AI +1
Robust Transfer Learning with Side Information
Mar 9, 2026Akram S. Awad, Shihab Ahmed, Yue Wang +1Reinforcement Learning Robust Markov Decision Processes
Department of Electrical and Computer Engineering, University of Central Florida, USA · Department of Computer Science, University of Central Florida, USA
Learning Optimal Distributionally Robust Individualized Treatment Rules Integrating Multi-Source Data
Mar 5, 2026Wenhai Cui, Wen Su, Xingqiu ZhaoDistribution Shift Robustness Distributionally Robust Optimization
Department of Applied Mathematics, The Hong Kong Polytechnic University · Department of Biostatistics, City University of Hong Kong
Risk-Averse Wasserstein Distributionally Robust Online Learning
Feb 23, 2026Guixian Chen, Salar Fattahi, Soroosh ShafieeDistributionally Robust Optimization Decision-Making under Uncertainty
University of Michigan · Cornell University
Differentially Private Non-convex Distributionally Robust Optimization
Feb 18, 2026Difei Xu, Meng Ding, Zebin Ma +4Distributionally Robust Optimization Differential Privacy
Provable Responsible AI and Data Analytics (PRADA) Lab · King Abdullah University of Science and Technology · State University of New York at Buffalo +1
Contextual Distributionally Robust Optimization with Causal and Continuous Structure
Jan 16, 2026Fenglin Zhang, Jie WangStochastic Optimization Distributionally Robust Optimization
School of Artificial Intelligence The Chinese University of Hong Kong, Shenzhen Shenzhen, 518172, China · School of Artificial Intelligence, School of Data Science The Chinese University of Hong Kong, Shenzhen Shenzhen, 518172, China
BalDRO: A Distributionally Robust Optimization based Framework for Large Language Model Unlearning
Jan 14, 2026Pengyang Shao, Naixin Zhai, Lei Chen +4Distributionally Robust Optimization LLM Unlearning
National University of Singapore Singapore · University of Science and Technology of China Hefei, China · Hefei University of Technology Hefei, China
Distributionally Robust Markov Games with Average Reward
Aug 5, 2025Zachary Roch, Yue WangNash Equilibrium Computation Multi-Agent System Optimization
Department of Electrical and Computer Engineering, University of Central Florida, Orlando, Florida, USA. · Department of Computer Science, University of Central Florida, Orlando, Florida, USA.
Improving Mixup Calibration with Wasserstein Distributionally Robust Optimization
Jun 22, 2025Jiaming Hu, Yeping Jin, Debarghya Mukherjee +1Image Corruption Robustness Data Augmentation
Department of Mathematics & Statistics Boston University · Department of Electrical and Computer Engineering, Division of Systems Engineering Department of Biomedical Engineering Faculty of Computing & Data Sciences Boston University
Distributionally Robust Deep Q-Learning
May 25, 2025Chung I Lu, Julian Sester, Aijia ZhangRobust Markov Decision Processes Deep Q-Learning
National University of Singapore, Department of Mathematics, 21 Lower Kent Ridge Road, 119077.
StablePCA: Distributionally Robust Learning of Shared Representations from Multi-Source Data
May 2, 2025Zhenyu Wang, Molei Liu, Jing Lei +2Principal Component Analysis Shared Representation Learning
Department of Statistics, Rutgers University · Department of Biostatistics, Peking University Health Science Center; Beijing International Center for Mathematical Research · Department of Statistics, Carnegie Mellon University +2
Wasserstein Distributionally Robust Regret Optimization
Apr 15, 2025Lukas-Benedikt Fiechtner, Jose BlanchetDistributionally Robust Optimization Robust Optimization
Institute of Computational and Mathematical Engineering Stanford University · Institute of Computational and Mathematical Engineering Department of Management Science and Engineering Stanford University
A stochastic smoothing framework for nonconvex-nonconcave minEmax problems with applications to Wasserstein distributionally robust optimization
Feb 24, 2025Wei Liu, Muhammad Khan, Gabriel Mancino-Ball +1Randomized Smoothing Nonconvex Stochastic Optimization
Department of Applied Mathematics, Hong Kong Polytechnic University, Hong Kong, China · Institute for Math & AI, Wuhan (IMAI), Wuhan university, China · Department of Mathematical Sciences Rensselaer Polytechnic Institute, Troy, NY, USA
Distributionally Robust Optimization via Iterative Algorithms in Continuous Probability Spaces
Dec 29, 2024Linglingzhi Zhu, Yunqin Zhu, Yao XieDistributionally Robust Optimization Wasserstein Distributionally Robust Optimization
1H. Milton Stewart School of Industrial and Systems Engineering Georgia Institute of Technology
A Distributionally Robust Optimisation Approach to Fair Credit Scoring
Feb 2, 2024Pablo Casas, Huan Yu, Christophe MuesDistribution Shift Robustness Financial Services
Southampton Business School, University of Southampton, Southampton, SO16 7QF, United Kingdom
Distributionally Robust Regularization of Sparse Integer Programming Trained Learning Models
Nov 3, 2023Sanjeeb Dash, Soumyadip Ghosh, Joao Goncalves +1Rule-Based Classification Interpretable ML
IBM Research, Yorktown Heights, NY 10598
Guided Adversarial Robust Transfer Learning with Source Mixing
Sep 12, 2023Xin Xiong, Zijian Guo, Tianxi CaiAdversarial Robustness Distributionally Robust Optimization
Harvard T.H. Chan School of Public Health, Boston, MA, USA · Center for Data Science, Zhejiang University, Zhejiang, China · Harvard Medical School, Boston, MA, USA
Learning from a Biased Sample
Sep 5, 2022Roshni Sahoo, Lihua Lei, Stefan WagerDistribution Shift Robustness Distributionally Robust Optimization
Stanford University

Apr 1, 2026J/K move · Enter open · S save

Stein Variational Uncertainty-Adaptive Model Predictive Control

Hrishikesh Sathyanarayan, Ian Abraham

Department of Mechanical Engineering, Yale University, USA · Department of Electrical Engineering, University of Sydney, Australia

Model Predictive Control Nonlinear MPC Distributionally Robust Optimization

Open paper AskPDF arXiv

We propose a Stein variational distributionally robust controller for nonlinear dynamical systems with latent parametric uncertainty. The method is an alternative to conservative worst-case ambiguity-set optimization with a deterministic particle-based approximation of a task-dependent uncertainty distribution, enabling the controller to concentrate on parameter sensitivities that most strongly affect closed-loop performance. Our method yields a controller that is robust to latent parameter uncertainty by coupling optimal control with Stein variational inference, and avoiding restrictive parametric assumptions on the uncertainty model while preserving computational parallelism. In contrast to classical DRO, which can sacrifice nominal performance through worst-case design, we find our approach achieves robustness by shaping the control law around relevant uncertainty that are most critical to the task objective. The proposed framework therefore reconciles robust control and variational inference in a single decision-theoretic formulation for broad classes of control systems with parameter uncertainty. We demonstrate our approach on representative control problems that empirically illustrate improved performance-robustness tradeoffs over nominal, ensemble, and classical distributionally robust baselines.