Importance Weighting

Follow this topic Ask about this topic

Importance weighting changes how much observations or other elements contribute to learning and evaluation, often to correct a mismatch between the data available and the population or policy of interest. It is used in domain adaptation, off-policy evaluation, label-shift correction, and to prioritize features, tokens, or tasks. Methods range from density-ratio estimation and inverse-propensity weighting to bounded or normalized weights, moment matching, and learned reweighting, sometimes paired with outcome models or formal uncertainty guarantees. A central challenge is balancing bias correction against the high variance and instability that can arise from extreme weights, especially when distributions have limited overlap or the assumed shift is wrong.

Latest papers

30 papers1 paper in the last four weeks, down 80% on the four weeks before. 0.0% of all new papers.

Latent-Space Importance Weighting under Covariate Shift
Oct 11, 2026Yuling Jiao, Lican Kang, Yang Xiang +2Covariate Shift Transfer Learning
School of Artificial Intelligence, and Hubei Key Laboratory of Computational Science, Wuhan University, Wuhan, 430072, China · Institute for Math and AI, Wuhan University, Wuhan, 430072, China · Department of Mathematics, The Hong Kong University of Science and Technology, Hong Kong, China, and Algorithms of Machine Learning and Autonomous Driving Research Lab, HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute, Shenzhen, China +2
From matrix inversion to constraints: provably tighter confidence regions for importance weights in label shift
Sep 13, 2026Mushan Li, Kihyun Han, Yanyuan MaLabel Shift Confidence Region Estimation
Department of Statistics, The Pennsylvania State University University Park, PA 16802, USA
Mind Which Bird You Favour: Parameterizing Adequacy-Fluency Balance in Meta-Evaluation of Machine Translation
Sep 13, 2026Behzad Shayegh, Niloofar KazemiImportance Weighting MT Evaluation
Independent Researchers
When Edit Localization Amplifies Relative Selection Bias: Gradient Geometry, Target Mismatch, and Importance Weighting
Sep 12, 2026Shengwei Zhang, Haoda Dai, Yifei Li +1Selection Bias Importance Weighting
University of Pennsylvania
Importance Weighting for Unlabeled-unlabeled Learning under Distribution Shift
Sep 10, 2026Atsutoshi Kumagai, Tomoharu Iwata, Hiroshi Takahashi +3Distribution Shift Importance Weighting
NTT, Inc.
From Citations to Contributions: LLM-Assisted Credit Scoring of Research Articles
Sep 7, 2026Sana Ebrahimi, Suraj Shetiya, Abolfazl AsudehImportance Weighting Bibliometric Analysis
University of Illinois Chicago · IIT Bombay
Balance of Benchmarks: Semantic Density Reweighting for Task-Conditioned Model Comparison
Aug 30, 2026Jhen-Ke Lin, Hong-Yun LinLLM Evaluation Benchmark Design
National Yang Ming Chiao Tung University
Safe Domain Adaptation for Physics: Overcoming Nuisances, Label Shifts, and Simulation Priors
Aug 18, 2026Ivan KharukDomain Adaptation Domain-Adversarial Learning
Institute for Nuclear Research of the Russian Academy of Sciences · Moscow Institute of Physics and Technology · Institute for Nuclear Research of the Russian Academy of Sciences, 60th October Anniversary Prospect 7a, Moscow, 117312, Russia +1
When Can You Trust Offline Evaluation of Equal-Cost Top-k Allocation? A Controlled, Reproducible Benchmark and Practitioner's Guide
Aug 12, 2026Binshuang LiInverse Probability Weighting Causal Effect Estimation
Independent Researcher
SSPO: Structure-Aware Similarity-Weighted Preference Optimization for Neural Combinatorial Optimization
Aug 12, 2026Yuanyu Li, Jintao Xu, Zijiang Liu +6Combinatorial Optimization Preference Optimization
Supply Chain Tech Team Y, JD.com, Beijing, China · Department of Industrial Engineering, Tsinghua University, Beijing, China · Faculty of Engineering and Faculty of Business and Economics, The University of Hong Kong, Hong Kong, China
Unsupervised Domain Adaptation for Multitask Image Analysis in Realistic Context with Extreme Label Shift; Application to the CTAO first Large Sized Telescope
Aug 10, 2026Michaël Dell'aiera, Thomas Vuillaume, Alexandre BenoitClass-Imbalanced Learning Label Shift
CNRS LAPP, Annecy, 74940, France · Université Savoie Mont Blanc LISTIC, Annecy, 74940, France
ReCo: Reweighting GRPO Against Distributional Concentration
Jul 29, 2026Junoh Park, Junseo Hwang, Wonguk Cho +1Reasoning Diversity RL for Language Model Reasoning
Graduate School of Data Science, Seoul National University
Kernel weighted importance sampling for off-policy evaluation in contextual bandits
Jul 16, 2026Joshua Spear, Matthieu Komorowski, Rebecca Pope +2Off-Policy Evaluation Importance Sampling
Institute of Child Health, University College London · Strive Health Ltd. · National Institute for Health Research +3
Heat-Kernel Entropy Profiles and Geometric Effective Sample Size for Weighted Measures on Manifolds
Jul 7, 2026Kisung YouImportance Sampling Importance Weighting
Baruch College
On the Position Bias of On-Policy Distillation
Jun 21, 2026Yan Xie, Sijie Zhu, Tiansheng Wen +2Importance Weighting Language Model Distillation
Xidian University · Georgia Institute of Technology · Amazon AGI SF Lab
Entropic Projection Alignment: Estimating, Explaining, and Improving Model Performance Under Distribution Shift
May 29, 2026Salim I. Amoukou, Emanuele Albini, Tom Bewley +2Distribution Shift Robustness Unsupervised Domain Adaptation
J.P. Morgan AI Research
Quotient DAGs for Off-Policy Evaluation:Forward-Flow Importance Sampling and Exact Slate Propensities
May 28, 2026Ziwen Xie, Shaowen Xiang, Hongyu He +1Off-Policy Evaluation Importance Sampling
Shanghai Jiao Tong University · National University of Singapore
Accelerated Dynamic Importance Weighting with Versatile Divergence-Minimizing Estimators
May 25, 2026Tongtong Fang, Nan Lu, Gang Niu +2Importance Weighting Instance Reweighting
The Institute of Statistical Mathematics, Tokyo, Japan. · University of Bristol, Bristol, U.K. · RIKEN Center for Advanced Intelligence Project, Tokyo, Japan. +1
Anytime PAC-Bayes for Constrained Density-Ratio Networks under Covariate Shift
May 17, 2026Paulo Akira F. Enabe, Rodrigo ProvasiPAC-Bayesian Generalization Bounds Domain Adaptation
Escola Politénica University of São Paulo Department of Structural and Geotechnical Engineering
TILT: Target-induced loss tilting under covariate shift
May 14, 2026Kakei Yamamoto, Martin J. WainwrightUnsupervised Domain Adaptation Distribution Shift
Lab for Information and Decision Systems · Statistics and Data Science Center · EECS† +2
BEACON: Cross-Domain Co-Training of Generative Robot Policies via Best-Effort Adaptation
May 9, 2026Antong Zhang, Han Qi, Heng YangSynthetic-to-Real Domain Adaptation Robot Policy Learning
Department of Computer Science, Brown University · School of Engineering and Applied Sciences, Harvard University
Weighting What Matters: Boosting Sample Efficiency in Medical Report Generation via Token Reweighting
Apr 22, 2026Alexander Weers, Daniel Rueckert, Martin J. MentenMedical Report Generation Healthcare
TUM School of Computation, Information and Technology, Technical University of Munich, DE · Munich Center for Machine Learning (MCML), DE · Department of Computing, Imperial College London, UK
A Mechanistic Analysis of Sim-and-Real Co-Training in Generative Robot Policies
Apr 15, 2026Yu Lei, Minghuan Liu, Abhiram Maddukuri +2Robot Policy Learning Synthetic-to-Real Domain Adaptation
Department of Computer Science, The University of Texas at Austin · Amazon FAR · NVIDIA
Gradient-Free Continual Learning in Spiking Neural Networks via Inter-Spike Interval Regularization
Apr 14, 2026Samrendra Roy, Kazuma Kobayashi, Souvik Chakraborty +2Spiking Neural Networks Catastrophic Forgetting
University of Illinois Urbana-Champaign, Department of Nuclear, Plasma & Radiological Engineering, Urbana, IL, USA · Indian Institute of Technology Delhi, Department of Applied Mechanics, New Delhi, India · University of Texas at El Paso, Department of Computer Science, El Paso, TX, USA +1
Heterogeneous Graph Importance Scoring and Clustering with Automated LLM-based Interpretation
Apr 9, 2026Takato YasunoImportance Weighting
Yachiyo Engineering Co., Ltd., Japan
Rethinking Data Mixing from the Perspective of Large Language Models
Apr 9, 2026Yuanjian Xu, Tianze Sun, Changwei Xu +7LLM Training Importance Weighting
Hong Kong University of Science and Technology (Guangzhou) · Harbin Institute of Technology University · OpenCSG +1
Not Worth Mentioning? A Pilot Study on Salient Proposition Annotation
Mar 28, 2026Amir Zeldes, Katherine Conhaim, Lauren LevineImportance Weighting
Department of Linguistics, Georgetown University
From Weighting to Modeling: A Nonparametric Estimator for Off-Policy Evaluation
Mar 10, 2026Rong J. B. ZhuOff-Policy Evaluation Inverse Probability Weighting
Institute of Science and Technology for Brain-inspired Intelligence, Fudan University
PreSight: Preoperative Outcome Prediction for Parkinson's Disease via Region-Prior Morphometry and Patient-Specific Weighting
Mar 2, 2026Yand Wang, Chen Zhang, Lanyun Zhu +6Clinical Outcome Prediction Clinical Decision-Making
Beijing Jiaotong University · Nanyang Technological University · Institute of Medical Technology, Peking University +3
Feature weighting for data analysis via evolutionary simulation
Nov 9, 2025Aris Daniilidis, Alberto Domínguez Corella, Philipp WissgottReplicator Dynamics Importance Weighting
Institut für Stochastik und Wirtschaftsmathematik, Variational Analysis, Dynamics and Operations Research Unit E105-04, Technische Universität Wien, Wiedner Hauptstraße 8, 1040 Vienna, Austria · Institut für Mathematik und Wissenschaftliches Rechnen, Universität Graz, Heinrichstraße 36, A-8010 Graz, Austria · danube.ai solutions gmbh, 1040 Vienna, Austria

Oct 11, 2026J/K move · Enter open · S save

Latent-Space Importance Weighting under Covariate Shift

Yuling Jiao, Lican Kang, Yang Xiang, Jerry Zhijian Yang+1

School of Artificial Intelligence, and Hubei Key Laboratory of Computational Science, Wuhan University, Wuhan, 430072, China · Institute for Math and AI, Wuhan University, Wuhan, 430072, China · Department of Mathematics, The Hong Kong University of Science and Technology, Hong Kong, China, and Algorithms of Machine Learning and Autonomous Driving Research Lab, HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute, Shenzhen, China+2

Covariate Shift Transfer Learning Importance Weighting Predictive Representation Learning

Open paper AskPDF arXiv

In this work, we propose a transfer learning algorithm for covariate shift, integrating sample reweighting with representation learning. A key feature of our approach is the use of a lower-dimensional latent space for modeling, in contrast to conventional methods that operate directly in the high-dimensional ambient space. Our method estimates the density ratio of learned latent features for downstream weighted prediction. We establish explicit target-domain excess-risk rates with independent data folds for strictly sufficient learned representations with regular learned-space prediction scores and density ratios. We give dimension comparisons under stated smoothness conditions and a variance comparison for true weights and a fixed predictor. General finite-sample inequalities retain representation-quality errors. Experiments on simulated and real-world datasets demonstrate gains from combining learned representations and latent weighting, and reveal sensitivity to initialization and domain choice.