Distribution Shift

Follow this topic Ask about this topic

Momentum

19 papers in the last four weeks, up 280% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 123

All topics

Density Ratio Estimation with Stein Displacement Fields
Oct 8, 2026Song LiuDensity Ratio Estimation Distribution Shift
University of Bristol
AutoAdapt: Reliable Few-Shot Adaptation under Clinical Distribution Shifts
Oct 8, 2026Song Wang, Jie Peng, Davis Hobley +2Few-Shot Domain Adaptation Domain Adaptation
Foci
Diagnosing and Recovering from Observation-Space Shift at Long-Horizon Skill Seams
Oct 7, 2026Pranav Wagh, Yu Fang, Yue Yang +1Long-Horizon Robotic Manipulation Robot Skill Learning
Department of Computer Science, University of North Carolina at Chapel Hill, NC, USA.
Beyond Policy Support: Interaction Constrained Offline Reinforcement Learning for Autonomous Driving
Oct 7, 2026Mahmoud Selim, Cristina Cipriani, Karl Henrik JohanssonOffline RL Distribution Shift
KTH Royal Institute of Technology
Retrieval-Based In-Context Learning: A Domain Adaptation Framework
Oct 5, 2026Yilun Zhu, Naihao Deng, Yingcong Li +2Distribution Shift Domain Adaptation
University of Michigan. · New Jersey Institute of Technology. · Northwestern University.
Zero Flux: Flow-Based Comparison of High-Dimensional Discrete Distributions
Oct 1, 2026Leyang Wang, Yakun Wang, Song Liu +1Distribution Shift Distribution Shift Detection
Department of Mathematical Informatics, The University of Tokyo, Japan · Center for Advanced Intelligence Project, RIKEN, Japan · School of Mathematics, University of Bristol, United Kingdom
Autoregressive Drillhole Modelling Under Distribution Shift
Oct 1, 2026Yihao Ding, Daniel Yitian Su, Yiran Zhang +2Distribution Shift Autoregressive Modeling
The University of Western Australia Crawley, WA 6009, Australia
Parameter-Efficient Distributionally Robust Adaptation of Tabular Foundation Models under Subpopulation Shift
Oct 1, 2026Seonghwi Kim, Sung Ho Jo, Minwoo ChaeDistribution Shift Robustness Tabular Foundation Models
Pohang University of Science and Technology
When to Adapt: Multi-Signal Domain Shift Detection for Efficient Training-Free Adaptation in Open-Vocabulary Segmentation
Sep 29, 2026Michele Antonazzi, Alejandra C. Hernandez, José Araujo +2Distribution Shift Continual Test-Time Adaptation
EECS and Digital Futures, KTH Royal Institute of Technology, Stockholm, Sweden · Ericsson Research, Ericsson AB, Stockholm, Sweden
Not Every Correction Helps: Gain-Guided Continual Test-Time Adaptation
Sep 29, 2026Youjia Zhang, Huiling Liu, Soyun Choi +2Adaptive Inference Test-Time Adaptation
Sungkyunkwan University · Nanyang Technological University
Adapting neural operators for mechanics decisions under changing operating conditions
Sep 27, 2026Prashant K. Jha, Koffi Enakoutsa, Ian Galloway +1Neural Surrogate Modeling Surrogate-Assisted Optimization
Department of Mechanical Engineering, South Dakota School of Mines and Technology, Rapid City, SD 57701, USA · Department of Mathematics, University of California, Los Angeles, Los Angeles, CA 90095, USA
Behavioral Monitoring of JEPA World Models with Jacobian Centroids
Sep 27, 2026Thomas Walker, Randall Balestriero, Richard BaraniukDistribution Shift World Model-Based Planning
Rice University · Brown University
RAEGL: Risk-Aware Evidence-Gated Learning for Selective Contextual Routing under Temporal Shift
Sep 27, 2026Yifan GuoDistribution Shift Selective Prediction
Stony Brook University
Temporal Generalization and Explanation Stability of Control Flow Graph Neural Networks for Malware Detection
Sep 21, 2026Md. Asif Sajeed, Md. Nazrul Islam Mondal, Md Ashraful Hossen AkashGraph Neural Networks Distribution Shift
Department of Computer Science and Engineering, Rajshahi University of Engineering & Technology, Rajshahi, 6204, Bangladesh
A Latent Distribution Perspective on Evaluating and Improving Latent Generative Models
Sep 21, 2026Xianghong Fang, Wenjie Shu, Tongda Xu +3Distribution Shift Generative AI Evaluation
University of Toronto · Independent · Vijil
ArtifactBench: Lineage-Aware Evaluation of AI-Generated Music Detectors under Distribution Shift
Sep 20, 2026Heewon OhData Leakage Distribution Shift
Intrect
Refuse, Decompose, Refresh: A Claim-Safe Protocol for Closed-Loop AI Evaluation
Sep 17, 2026Peiying Zhu, Sidi ChangDistribution Shift
Blossom AI San Francisco, CA, USA
Learning under Target Shift: Optimal Density Ratio Estimation and Importance-Weighted Regression
Sep 14, 2026Ren-Rui Liu, Zheng-Chu GuoKernel Regression Distribution Shift
School of Mathematical Sciences, Zhejiang University, Hangzhou 310058, China
The Anatomy and Boundary of Adaptation under Temporal Tabular Shift
Sep 14, 2026Tianyu Wang, Xi Vincent Wang, Lihui Wang +2Tabular Foundation Models Distribution Shift
Department of Production Engineering, KTH Royal Institute of Technology, Stockholm, Sweden · Global Institute of Future Technology, Shanghai Jiao Tong University, Shanghai, China
Importance Weighting for Unlabeled-unlabeled Learning under Distribution Shift
Sep 12, 2026Atsutoshi Kumagai, Tomoharu Iwata, Hiroshi Takahashi +3Distribution Shift Importance Weighting
NTT, Inc.
General Quantification of Covariate and Concept Shifts
Sep 12, 2026Hongbo Chen, Li Charlie XiaDistribution Shift Concept Drift
Department of Statistics and Financial Mathematics, School of Mathematics, South China University of Technology, Guangzhou, China.
Accountable and uncertainty-aware evaluation of sensor-based AI under distribution shift: devices, subjects, and nearly three years underground
Sep 8, 2026Benny Platte, Rico Thomanek, Christian Roschke +1AI Accountability Uncertainty Quantification
Mittweida University of Applied Sciences · Faculty of Applied Computer Sciences and Biosciences, Mittweida University of Applied Sciences, Mittweida, Germany
Vision: Data-Centric Anchoring for Robust and Interpretable Agentic AI
Sep 8, 2026Arun Vignesh Malarkkan, Xinyuan Wang, Yanjie FuAI Agent Reliability Distribution Shift
School of Computing and Augmented Intelligence, Arizona State University, USA
Semi-Supervised Learning under Spatially Biased Sampling
Sep 7, 2026Bright Wiredu Nuakoh, Francky Fouedjio, Stephen Bradshaw +4Distribution Shift Semi-Supervised Learning
African Institute for Mathematical Sciences (AIMS), 17 KN 16 Ave, Kigali, Rwanda · Mathematical Application & Data Analytics Group, School of Science, Edith Cowan University, 270 Joondalup Drive, Joondalup, WA 6027, Australia · Data & Analytics, Rio Tinto, 152-158 St Georges Terrace, Perth, WA 6000, Australia +2
MultiGhostBench: A Multilingual Benchmark for Long-Form LLM-Generated Text Attribution under Distribution Shifts
Sep 2, 2026Matteo Greco, Anudeex Shetty, Andrea Tagarelli +1Authorship Attribution Cross-Lingual Transfer
School of Computing and Information Systems, The University of Melbourne, Australia · DIMES Dept., University of Calabria, Italy
ProxPI: Proximal Prior Injection for Sampling-Based MPC under Learned-Prior Mismatch
Sep 1, 2026Euncheol Im, Myotaeg Lim, Yisoo LeeDistribution Shift Model Predictive Control
Center for Humanoid Research, Korea Institute of Science and Technology (KIST), 02792 Seoul, South Korea · School of Electrical Engineering, Korea University, 02841 Seoul, South Korea
Quantifying geographic domain shift to decouple the geospatial transferability of human mobility flow generation models
Aug 21, 2026Zhiyong Zhou, Song Gao, Qianheng Zhang +2Spatial Generalization Task Transferability Estimation
GeoDS Lab, Department of Geography, University of Wisconsin-Madison, Madison, WI, USA · School of Earth Sciences & Zhejiang Key Laboratory of Geographic Information Science, Zhejiang University, Hangzhou, China
Regime-Conditional Verification: Correctness Estimation for Adapting and Monitoring Safety Classifiers
Aug 14, 2026Thiago Sandoval, Ufuk TopcuDistribution Shift Selective Prediction
The University of Texas at Austin
Thermodynamics of Learning: A Typed Four-Component Accounting of Memory, Fit, and Value
Aug 13, 2026Akihito SudoStatistical Physics of Learning Distribution Shift
ZeroStruct Inc.
HNR-DAC: Hard-Negative Reranking and Distribution-Aligned Classification for Scientific Claim Verification
Aug 7, 2026Zhenchao Wang, Xin Chen, Luoxi Zhang +2Claim Verification Distribution Shift
Southern University of Science and Technology, Shenzhen, China · Institute of Artificial Intelligence, Shenzhen University of Advanced Technology, Shenzhen, China · Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China

Oct 8, 2026, stat.MLJ/K move · Enter open · S save

Density Ratio Estimation with Stein Displacement Fields

Song Liu

University of Bristol

Density Ratio Estimation Distribution Shift

Open paper AskPDF arXiv

Density ratios quantify distribution shift from a probability-mass point of view, whereas displacement fields describe, from a dynamical point of view, how one distribution is transported onto another. Although both offer complementary insights, they are usually estimated separately, and converting one into the other requires post-processing. In this paper, we estimate the density ratio between a target and a base distribution by parametrizing it through a displacement field acting on the base: the log-ratio is modeled as minus the Stein operator of the base applied to the field, up to a normalizing constant. This gives both statistical and dynamical descriptions of the distribution shift through a single convex optimization problem. Iterating this estimate-and-move step gives two inference algorithms: push-forward moves the model and corrects a pretrained sampler without retraining it, whereas pull-back moves the data closer to the base and fits a transformation model one layer at a time. Applications to distribution shift in simulation-based inference and to nonlinear independent component analysis illustrate the benefits and limitations of the approach.

Momentum

Related topics

Latest papers 123