Distribution Shift Robustness

Ask about this topic

Overview

The field asks how models can remain accurate, calibrated, and fair when data change across time, locations, populations, or conditions, including shifts in inputs, labels, and their relationships. Approaches include distributionally robust optimization, invariant and causal representations, targeted data augmentation, test-time adaptation, and conformal methods that adjust predictions or quantify uncertainty. Evaluation increasingly uses temporal and cross-domain tests, realistic corruption benchmarks, and worst-group measures rather than relying only on random train-test splits. A central tension is that adapting to a new domain can improve its performance but also cause instability or forget earlier capabilities, while guarantees that cover broad shifts may produce overly conservative predictions.

Latest papers

CardsList

285 papers34 papers in the last four weeks, up 31% on the four weeks before. 0.2% of all new papers.

  1. Robust Conditional Conformal Prediction via Branched Normalizing Flow

    May 3, 2026Rui Xu, Xingyuan Chen, Wenxing Huang +4Distribution Shift RobustnessNormalizing Flows

    Information Hub, The Hong Kong University of Science and Technology (Guangzhou) · The Second Affiliated Hospital of Guangzhou Medical University

  2. Perturb and Correct: Post-Hoc Ensembles using Affine Redundancy

    May 2, 2026Eleanor QuintDistribution Shift RobustnessEnsemble Learning

    Department of Computing University of Nebraska–Lincoln Lincoln, NE 68508, USA

  3. Sampler-Robust Optimization under Generative Models

    Apr 30, 2026Ziwei Zhang, Jonathan Yu-Meng LiDistribution Shift RobustnessDistributionally Robust Optimization

    Telfer School of Management University of Ottawa

  4. Detecting is Easy, Adapting is Hard: Local Expert Growth for Visual Model-Based Reinforcement Learning under Distribution Shift

    Apr 30, 2026Haiyang ZhaoDistribution Shift RobustnessOOD Generalization

    University of Georgia United States

  5. Robustness of Transformer-Based Fluence Map Prediction Under Clinically Realistic Perturbations

    Apr 28, 2026Ujunwa Mgboh, Rafi Ibn Sultan, Joshua Kim +2Distribution Shift RobustnessTransformer

    Wayne State University, Detroit, MI, USA · Henry Ford Health, Detroit, MI

  6. Robustness Evaluation of a Foundation Segmentation Model Under Simulated Domain Shifts in Abdominal CT: Implications for Health Digital Twin Deployment

    Apr 28, 2026Sanghati BasuDistribution Shift RobustnessImage Segmentation

    Healthcare Informatics, University of Illinois Springfield

  7. Robust and Clinically Reliable EEG Biomarkers: A Cross Population Framework for Generalizable Parkinson's Disease Detection

    Apr 27, 2026Nicholas R. Rasmussen, Longwei Wang, Rodrigue Rizk +5Distribution Shift RobustnessElectroencephalography

    USD AI Research, Department of Computer Science, University of South Dakota, Vermillion, SD 57069, USA · Biomedical and Translational Sciences, Sanford School of Medicine, University of South Dakota, Vermillion, SD 57069, USA · Department of Sport, Exercise and Rehabilitation, Northumbria University, Newcastle upon Tyne, NE1 8ST, United Kingdom +1

  8. Local Neighborhood Instability in Parametric Projections: Quantitative and Visual Analysis

    Apr 23, 2026Frederik L. Dennig, Daniel A. KeimDistribution Shift RobustnessJacobian Regularization

    University of Konstanz, Germany

  9. Supervised Learning Has a Necessary Geometric Blind Spot: Theory, Consequences, and Minimal Repair

    Apr 23, 2026Vishal RajputAdversarial TrainingRepresentation Geometry

    1KU Leuven, Belgium.

  10. Evaluating Histogram Matching for Robust Deep learning-Based Grapevine Disease Detection

    Apr 21, 2026Ruben Pascual, Inés Hernández, Salvador Gutiérrez +4Distribution Shift RobustnessImage Enhancement

    Institute of Smart Cities (ISC), Dept. of Statistics, Computer Science and Mathematics, Public Univ. of Navarre (UPNA), 31006 Pamplona, Spain · Institute of Grapevine and Wine Sciences (Univ. of La Rioja, CSIC, Govt. of La Rioja), 26007, Logroño, Spain and Televitis Research Group, Univ. of La Rioja, 26006, Logroño, Spain · Dept. of Computer Science and AI, Univ. of Granada, 18071, Granada, Spain +1

  11. LLM-AUG: Robust Wireless Data Augmentation with In-Context Learning in Large Language Models

    Apr 20, 2026Pranshav Gajjar, Manan Tiwari, Sayanta Seth +1Distribution Shift RobustnessSynthetic Data Augmentation

    NextG Wireless Lab, North Carolina State University, NC

  12. Dual Strategies for Test-Time Adaptation

    Apr 19, 2026Nam Nguyen Phuong, Duc Nguyen The Minh, Phi Le Nguyen +2Distribution Shift RobustnessTest-Time Adaptation

    Institute for AI Innovation and Societal Impact, Hanoi University of Science and Technology · Monash University · Adelaide University

  13. Test-Time Adaptation for EEG Foundation Models: A Systematic Study under Real-World Distribution Shifts

    Apr 18, 2026Gabriel Jason Lee, Jathurshan Pradeepkumar, Jimeng SunDistribution Shift RobustnessElectroencephalography

    University of Illinois Urbana-Champaign, Urbana, IL, USA

  14. Reversible Residual Normalization Alleviates Spatio-Temporal Distribution Shift

    Apr 17, 2026Zhaobo Hu, Vincent Gauthier, Mehdi NaimaInvertible Neural NetworksDistribution Shift Robustness

    SAMOVAR, Télécom SudParis · Institut Polytechnique de Paris · CNRS – LIP6 +1

  15. Robustifying and Selecting Cohort-Appropriate Prognostic Models under Distributional Shifts

    Apr 16, 2026Dimitris Bertsimas, Carol Gao, Angelos G. Koulouras +1Distribution Shift RobustnessModel Calibration

    Operations Research Center, Massachusetts Institute of Technology, Cambridge, MA, 02139, USA. · Sloan School of Management, Massachusetts Institute of Technology, Cambridge, MA, 02139, USA. · Department of Surgery, Memorial Sloan Kettering Cancer Center, New York, NY, 10065, USA. +1

  16. FAIR Universe Weak Lensing ML Uncertainty Challenge: Handling Uncertainties and Distribution Shifts for Precision Cosmology

    Apr 15, 2026Biwei Dai, Po-Wen Chang, Wahid Bhimji +15Uncertainty QuantificationDistribution Shift Robustness

    Institute for Advanced Study · Lawrence Berkeley National Laboratory · Université Paris-Saclay, CNRS/IN2P3, IJCLab +7

  17. Right Regions, Wrong Labels: Semantic Label Flips in Segmentation under Correlation Shift

    Apr 14, 2026Akshit Achara, Yovin Yahathugoda, Nick Byrne +4Semantic SegmentationDistribution Shift Robustness

    School of Biomedical Engineering & Imaging Sciences, King’s College London, UK

  18. Towards Successful Implementation of Automated Raveling Detection: Effects of Training Data Size, Illumination Difference, and Spatial Shift

    Apr 14, 2026Xinan Zhang, Haolin Wang, Zhongyu Yang +2Distribution Shift RobustnessStructural Health Monitoring

    James · School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA 30332 · School of Civil and Environmental Engineering, Georgia Institute of Technology, Atlanta, GA 30332

  19. Bias-Corrected Adaptive Conformal Inference for Multi-Horizon Time Series Forecasting

    Apr 14, 2026Ankit Lade, Sai Krishna J., Indar KumarAdaptive Conformal InferenceTime Series Forecasting

  20. Data-driven Reachable Set Estimation with Tunable Adversarial and Wasserstein Distributional Guarantees

    Apr 14, 2026Georgios Pantazis, Michelle S. ChongDistribution Shift Robustness

    Dynamics and Control (D&C) section at the Department of Mechanical Engineering, Eindhoven University of Technology, the Netherlands.

  21. Distributionally Robust K-Means Clustering

    Apr 13, 2026Vikrant Malik, Taylan Kargin, Babak HassibiClusteringDistribution Shift Robustness

    Department of Electrical Engineering, California Institute of Technology, Pasadena, CA 91125 USA. · California Institute of Technology, Pasadena, CA 91125 USA · Massachusetts Institute of Technology, Cambridge, MA 02139 USA.

  22. WBCBench 2026: A Challenge for Robust White Blood Cell Classification Under Class Imbalance

    Apr 12, 2026Xin Tian, Xudong Ma, Tianqi Yang +4White Blood Cell ClassificationMedical Image Classification

    University of Oxford, Oxford, United Kingdom · University College London, London, United Kingdom · University of Bristol, Bristol, United Kingdom +1

  23. Distributionally Robust PAC-Bayesian Control

    Apr 12, 2026Domagoj Herceg, Duarte AntunesDistribution Shift RobustnessPAC-Bayesian Generalization Bounds

    The authors are with the Department of Mechanical Engineering, Eindhoven university of Technology, Eindhoven, The Netherlands.

  24. IKKA: Inversion Classification via Critical Anomalies for Robust Visual Servoing

    Apr 9, 2026Darya PavlenkoVision-Based Robot ControlDistribution Shift Robustness

    Clausthal-Zellerfeld, Germany

  25. Tracking Adaptation Time: Metrics for Temporal Distribution Shift

    Apr 8, 2026Lorenzo Iovine, Giacomo Ziffer, Emanuele Della ValleDistribution Shift RobustnessTemporal Distribution Shift

    Politecnico di Milano, DEIB, Via Giuseppe Ponzio, 34, 20133 Milan, Italy

  26. Weighted Bayesian Conformal Prediction

    Apr 7, 2026Xiayin Lou, Peng LuoConformal PredictionWeighted Conformal Prediction

    Technical University of Munich · Massachusetts Institute of Technology

  27. CRISP: Rank-Guided Iterative Squeezing for Robust Medical Image Segmentation under Domain Shift

    Apr 7, 2026Yizhou Fang, Pujin Cheng, Yixiang Liu +2Image SegmentationMedical Image Segmentation

    Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China · The University of Hong Kong, Hong Kong, China · Jiaxing Research Institute, Southern University of Science and Technology, Jiaxing, China +1

  28. Generative models for decision-making under distributional shift

    Apr 6, 2026Xiuyuan Cheng, Yunqin Zhu, Yao XieDecision-Making under UncertaintyDistribution Shift Robustness

    Department of Mathematics, Duke University, Durham, NC, USA · H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, USA

  29. Learning Stable Predictors from Weak Supervision under Distribution Shift

    Apr 5, 2026Mehrdad Shoeibi, Elias Hossain, Ivan Garibay +1Distribution Shift RobustnessWeakly Supervised Learning

    University of Central Florida

  30. Measuring Robustness of Speech Recognition from MEG Signals Under Distribution Shift

    Apr 5, 2026Sheng-You Chien, Bo-Yi Mao, Yi-Ning Chang +1Distribution Shift RobustnessNeural Decoding

    Department of Computer Science, National Tsing-Hua University, Hsinchu, Taiwan