{"total":56,"rows":[{"id":"2108.13624","title":"Towards Out-Of-Distribution Generalization: A Survey","created":"2021-08-31","cited_by_count":436,"area":null},{"id":"2204.08040","title":"NICO++: Towards Better Benchmarking for Domain Generalization","created":"2022-04-17","cited_by_count":86,"area":null},{"id":"2107.00758","title":"The Spotlight: A General Method for Discovering Systematic Errors in Deep Learning Models","created":"2021-07-01","cited_by_count":63,"area":null},{"id":"2108.02943","title":"Unsupervised Learning of Debiased Representations with Pseudo-Attributes","created":"2021-08-06","cited_by_count":44,"area":null},{"id":"2204.07596","title":"Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learning","created":"2022-04-15","cited_by_count":40,"area":null},{"id":"2303.02011","title":"Diagnosing Model Performance Under Distribution Shift","created":"2023-03-03","cited_by_count":39,"area":null},{"id":"2206.07766","title":"Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalization","created":"2022-06-15","cited_by_count":38,"area":null},{"id":"2102.13128","title":"An Online Learning Approach to Interpolation and Extrapolation in Domain Generalization","created":"2021-02-25","cited_by_count":30,"area":null},{"id":"2112.12181","title":"Simple and near-optimal algorithms for hidden stratification and multi-group learning","created":"2021-12-22","cited_by_count":28,"area":null},{"id":"2103.02477","title":"Regularizing towards Causal Invariance: Linear Models with Proxies","created":"2021-03-03","cited_by_count":20,"area":null},{"id":"2111.02355","title":"A Theoretical Analysis on Independence-driven Importance Weighting for Covariate-shift Generalization","created":"2021-11-03","cited_by_count":19,"area":null},{"id":"2204.06340","title":"Distributionally Robust Models with Parametric Likelihood Ratios","created":"2022-04-13","cited_by_count":17,"area":null},{"id":"2211.12703","title":"Subgroup Robustness Grows On Trees: An Empirical Baseline Investigation","created":"2022-11-23","cited_by_count":17,"area":null},{"id":"2107.09947","title":"Preventing dataset shift from breaking machine-learning biomarkers","created":"2021-07-21","cited_by_count":15,"area":null},{"id":"2211.10508","title":"Distributionally Robust Survival Analysis: A Novel Fairness Loss Without Demographics","created":"2022-11-18","cited_by_count":15,"area":null},{"id":"2209.01754","title":"Learning from a Biased Sample","created":"2022-09-05","cited_by_count":14,"area":null},{"id":"2409.10538","title":"Fairness in Survival Analysis with Distributionally Robust Optimization","created":"2024-08-31","cited_by_count":14,"area":null},{"id":"2106.09467","title":"Algorithmic Bias and Data Bias: Understanding the Relation between Distributionally Robust Optimization and Data Curation","created":"2021-06-17","cited_by_count":13,"area":null},{"id":"2108.12250","title":"A comparison of approaches to improve worst-case predictive model performance over patient subpopulations","created":"2021-08-27","cited_by_count":12,"area":null},{"id":"2406.16756","title":"Addressing Polarization and Unfairness in Performative Prediction","created":"2024-06-24","cited_by_count":11,"area":null},{"id":"2502.08991","title":"Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks?","created":"2025-02-13","cited_by_count":11,"area":null},{"id":"2205.15947","title":"Evaluating Robustness to Dataset Shift via Parametric Robustness Sets","created":"2022-05-31","cited_by_count":10,"area":null},{"id":"2206.10915","title":"Understanding the effect of sparsity on neural networks robustness","created":"2022-06-22","cited_by_count":8,"area":null},{"id":"2403.13870","title":"ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations","created":"2024-03-20","cited_by_count":8,"area":null},{"id":"2106.04923","title":"Learning Domain Invariant Representations by Joint Wasserstein Distance Minimization","created":"2021-06-09","cited_by_count":6,"area":null},{"id":"2307.13381","title":"Scaff-PD: Communication Efficient Fair and Robust Federated Learning","created":"2023-07-25","cited_by_count":6,"area":null},{"id":"2307.15247","title":"Is this model reliable for everyone? Testing for strong calibration","created":"2023-07-28","cited_by_count":6,"area":null},{"id":"2307.10299","title":"Causality-oriented robustness: exploiting general noise interventions","created":"2023-07-18","cited_by_count":5,"area":null},{"id":"2311.05054","title":"Geometry-Calibrated DRO: Combating Over-Pessimism with Free Energy Implications","created":"2023-11-08","cited_by_count":5,"area":null},{"id":"2407.01316","title":"Evaluating Model Performance Under Worst-case Subpopulations","created":"2024-07-01","cited_by_count":5,"area":null},{"id":"2411.14055","title":"DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization","created":"2024-11-21","cited_by_count":5,"area":null},{"id":"2505.23565","title":"DRO: A Python Library for Distributionally Robust Optimization in Machine Learning","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2510.12769","title":"Sample-Efficient Omniprediction for Proper Losses","created":"2025-10-14","cited_by_count":5,"area":null},{"id":"2212.06338","title":"Minimax Optimal Estimation of Stability Under Distribution Shift","created":"2022-12-13","cited_by_count":4,"area":null},{"id":"2306.10081","title":"Optimizer's Information Criterion: Dissecting and Correcting Bias in Data-Driven Optimization","created":"2023-06-16","cited_by_count":4,"area":null},{"id":"2406.02426","title":"Contextual Optimization under Covariate Shift: A Robust Approach by Intersecting Wasserstein Balls","created":"2024-06-04","cited_by_count":4,"area":null},{"id":"2207.05777","title":"Long Term Fairness for Minority Groups via Performative Distributionally Robust Optimization","created":"2022-07-12","cited_by_count":3,"area":null},{"id":"2206.03515","title":"How does overparametrization affect performance on minority groups?","created":"2022-06-07","cited_by_count":2,"area":null},{"id":"2402.14929","title":"Federated Fairness without Access to Sensitive Groups","created":"2024-02-22","cited_by_count":2,"area":null},{"id":"2406.12243","title":"CherryRec: Enhancing News Recommendation Quality via LLM-driven Framework","created":"2024-06-18","cited_by_count":2,"area":null},{"id":"2410.09402","title":"Minimax rates of convergence for nonparametric regression under adversarial attacks","created":"2024-10-12","cited_by_count":2,"area":null},{"id":"2304.00305","title":"Predictive Heterogeneity: Measures and Applications","created":"2023-04-01","cited_by_count":1,"area":null},{"id":"2407.02268","title":"Footprints of Data in a Classifier: Understanding the Privacy Risks and Solution Strategies","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2408.09157","title":"On the KL-Divergence-based Robust Satisficing Model","created":"2024-08-17","cited_by_count":1,"area":null},{"id":"2502.01777","title":"CTC-DRO: Robust Optimization for Reducing Language Disparities in Speech Recognition","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2502.12413","title":"DivIL: Unveiling and Addressing Over-Invariance for Out-of- Distribution Generalization","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2509.24462","title":"Distributionally Robust Federated Learning with Outlier Resilience","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2107.04714","title":"A Topological-Framework to Improve Analysis of Machine Learning Model Performance","created":"2021-07-09","cited_by_count":0,"area":null},{"id":"2109.01558","title":"Learning Neural Models for Natural Language Processing in the Face of Distributional Shift","created":"2021-09-03","cited_by_count":0,"area":null},{"id":"2301.11724","title":"Meta-Learning Mini-Batch Risk Functionals","created":"2023-01-27","cited_by_count":0,"area":null},{"id":"2306.05937","title":"Robust Data-driven Prescriptiveness Optimization","created":"2023-06-09","cited_by_count":0,"area":null},{"id":"2311.18826","title":"Geometry-Aware Normalizing Wasserstein Flows for Optimal Causal Inference","created":"2023-11-30","cited_by_count":0,"area":null},{"id":"2506.00969","title":"Data Heterogeneity Modeling for Trustworthy Machine Learning","created":"2025-06-01","cited_by_count":0,"area":null},{"id":"2509.07955","title":"ACE and Diverse Generalization via Selective Disagreement","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2604.11507","title":"Deep Learning for Sequential Decision Making under Uncertainty: Foundations, Frameworks, and Frontiers","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2605.16219","title":"The Privacy Price of Tail-Risk Learning: Effective Tail Sample Size in Differentially Private CVaR Optimization","created":"2026-05-15","cited_by_count":0,"area":null}],"next_cursor":null}