Data to 14 Oct 2026

Learning Models with Uniform Performance via Distributionally Robust Optimization

arXiv 1810.08750 ↗First posted 20 Oct 2018stat.ML cs.LGcited by 335

Not on the map. Why?

Abstract (arXiv)

A common goal in statistics and machine learning is to learn models that can perform well against distributional shifts, such as latent heterogeneous subpopulations, unknown covariate shifts, or unmodeled temporal effects. We develop and analyze a distributionally robust stochastic optimization (DRO) framework that learns a model providing good performance against perturbations to the data-generating distribution. We give a convex formulation for the problem, providing several convergence guarantees. We prove finite-sample minimax upper and lower bounds, showing that distributional robustness sometimes comes at a cost in convergence rates. We give limit theorems for the learned parameters, where we fully specify the limiting distribution so that confidence intervals can be computed. On real tasks including generalizing to unknown subpopulations, fine-grained recognition, and providing good tail performance, the distributionally robust approach often exhibits improved performance.

Key facts. Cited by 335 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 41; 2022: 60; 2023: 69; 2024: 58; 2025: 60; 2026: 47.

335 papers.

Sort:

By area:

2021Towards Out-Of-Distribution Generalization: A Surveycited by 436
2023Change is Hard: A Closer Look at Subpopulation Shiftcited by 120
2022Robust Reinforcement Learning using Offline Datacited by 96
2021Heterogeneous Risk Minimizationcited by 90
2022Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexitycited by 87
2022Probable Domain Generalization via Quantile Risk Minimizationcited by 66
2022ZIN: When and How to Learn Invariance Without Environment Partition?cited by 58
2021DORO: Distributional and Outlier Robust Optimizationcited by 56
2024Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimizationcited by 53
2023The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Modelcited by 52
2022Out-of-distribution Generalization with Causal Invariant Transformationscited by 45
2023Model Agnostic Sample Reweighting for Out-of-Distribution Learningcited by 44

38 more

2023Improved Sample Complexity Bounds for Distributionally Robust Reinforcement Learningcited by 44
2021On Tilted Losses in Machine Learning: Theory and Applicationscited by 43
2021Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspectivecited by 40
2023Improving Fairness in Deepfake Detectioncited by 40
2021Non-convex Distributionally Robust Optimization: Non-asymptotic Analysiscited by 39
2022On-Demand Sampling: Learning Optimally from Multiple Distributionscited by 39
2023Diagnosing Model Performance Under Distribution Shiftcited by 39
2023A Finite Sample Complexity Bound for Distributionally Robust Q-learningcited by 36
2023Natural Actor-Critic for Robust Reinforcement Learning with Function Approximationcited by 36
2022Doubly Robust Distributionally Robust Off-Policy Evaluation and Learningcited by 34
2022A System-Level View on Out-of-Distribution Data in Roboticscited by 33
2022Distributionally Robust Offline Reinforcement Learning with Linear Function Approximationcited by 32
2022Minimax Regret Optimization for Robust Machine Learning under Distribution Shiftcited by 31
2022Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and Languagescited by 30
2021Modeling the Second Player in Distributionally Robust Optimizationcited by 29
2021Off-Policy Risk Assessment in Contextual Banditscited by 29
2022Understanding Why Generalized Reweighting Does Not Improve Over ERMcited by 29
2023Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimizationcited by 29
2023Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalizationcited by 29
2024AI-Face: A Million-Scale Demographically Annotated AI-Generated Face Dataset and Fairness Benchmarkcited by 28
2021Towards Theoretical Understandings of Robust Markov Decision Processes: Sample Complexity and Asymptoticscited by 27
2021Focus on the Common Good: Group Distributional Robustness Followscited by 25
2024Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertaintycited by 25
2021Kernelized Heterogeneous Risk Minimizationcited by 21
2023Understanding Contrastive Learning via Distributionally Robust Optimizationcited by 21
2024A Survey on Evaluation of Out-of-Distribution Generalizationcited by 21
2023Statistical Inference for Fairness Auditingcited by 20
2023Rethinking the Evaluation Protocol of Domain Generalizationcited by 20
2021A Theoretical Analysis on Independence-driven Importance Weighting for Covariate-shift Generalizationcited by 19
2025AVTrustBench: Assessing and Enhancing Reliability and Robustness in Audio-Visual LLMscited by 19
2021Distributionally Robust Multilingual Machine Translationcited by 18
2022How unfair is private learning ?cited by 18
2023On the Theories Behind Hard Negative Sampling for Recommendationcited by 18
2025Robust LLM Alignment via Distributionally Robust Direct Preference Optimizationcited by 18
2022Distributionally Robust Models with Parametric Likelihood Ratioscited by 17
2022Subgroup Robustness Grows On Trees: An Empirical Baseline Investigationcited by 17
2022Near-Optimal Algorithms for Group Distributionally Robust Optimization and Beyondcited by 17
2023Distributionally Robust Model-based Reinforcement Learning with Large State Spacescited by 17

50 most cited of 335 All 335 (JSON)