Adaptive Sampling

Follow this topic Ask about this topic

Adaptive sampling studies how to choose which examples, measurements, or computational steps to spend a limited budget on. Common approaches use uncertainty, prediction error, information gain, or difficulty to guide active learning, Bayesian experimental design, bandit allocation, and adaptive numerical solvers; learned policies, including reinforcement learning, are also used. Applications range from scientific experiments and sensor acquisition to diffusion-model sampling and test-time reasoning with language models. A central challenge is ensuring that the signals used to prioritize samples reliably improve the final task without sacrificing coverage, introducing bias, or costing more to compute than they save.

Latest papers

202 papers37 papers in the last four weeks, up 106% on the four weeks before. 0.2% of all new papers.

ShaplEIG: Bayesian Experimental Design for Shapley Value Estimation
Jun 1, 2026David Rundel, Fabian Fumagalli, Maximilian Muschalik +2Shapley Value Attribution Adaptive Sampling
Department of Statistics, LMU Munich, Munich, Germany · Munich Center for Machine Learning, Munich, Germany · Institute for Informatics, LMU Munich, Munich, Germany +2
Query-Limited Community Recovery in Stochastic Block Models
Jun 1, 2026Sabyasachi Basu, Manuj Mukherjee, Lutz Oettershagen +1Active Learning Adaptive Sampling
1Microsoft Research, India · 2Indraprastha Institute of Information Technology, India · University of Liverpool, United Kingdom +1
Improvise, Adapt, Overcome: An On-The-Fly Multifidelity Algorithm for Efficient Machine Learning
Jun 1, 2026Vivin Vinod, Peter ZaspelQuantum Chemistry Multifidelity Modeling
School of Mathematics and Natural Sciences, University of Wuppertal, Germany.
Learning Implicit Bias in Generative Spaces for Accelerating Protein Dynamics Emulation
Jun 1, 2026Kaihui Cheng, Zhiqiang Cai, Wenkai Xiang +4Diffusion Model Sampling Adaptive Sampling
Fudan University · Shanghai Academy of AI for Science · Shanghai Innovation Institute
Self-Regulating Annealing in Heavy-Tailed Diffusion Models
Jun 1, 2026Keito Wakatsuki, Hideaki ShimazakiStochastic Differential Equations Diffusion Sampling
Graduate School of Informatics Kyoto University, Kyoto, Japan
Meta-Black-Box Optimization with Ensemble Surrogate Modeling for Robustness-Accuracy Trade-off within SAEA
May 30, 2026Xiao Jin, Yongxiong Wang, Haobo Liu +2Surrogate Modeling Surrogate-Assisted Optimization
School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, 200093, Shanghai, China · Xinxiang University, 453003, Xinxiang, China · College of System Engineering, National University of Defense Technology, 410073, Changsha, China
PEEK: Picking Essential frames via Efficient Knowledge distillation
May 29, 2026Killian Steunou, Anas Filali Razzouki, Khalil Guetari +2Efficient VLM Inference Video Captioning
Télécom SudParis — SAMOVAR Institut Polytechnique de Paris Palaiseau, France · Moments Lab 69 Avenue Pierre Grenier Boulogne-Billancourt, France
Adaptive data selection improves wearable prediction under low baseline performance
May 29, 2026Ali KargarandehkordiData Selection Training Data Selection
Reasoning with Sampling: Cutting at Decision Points
May 28, 2026Felix Zhou, Anay Mehrotra, Quanquan C. LiuMarkov Chain Monte Carlo Efficient Language Model Reasoning
Yale University · Stanford University
VR-DAgger: Immersive VR for Dexterous Data Collection and Uncertainty-Guided On-Policy Correction
May 26, 2026René Zurbrügg, Tifanny Portela, Arjun Bhardwaj +3Robotic Data Collection Robot Teleoperation
The Authors are with the Robotics Systems Lab ETH Zürich.
Uncertainty-Aware Budget Allocation for Adaptive Test-Time Reasoning
May 26, 2026Manh Nguyen, Sunil Gupta, Hung LeEfficient Language Model Reasoning Adaptive Sampling
Applied Artificial Intelligence Initiative Deakin University, Australia
DynFrame: Adaptive Reasoning-Driven Multimodal Framework with Dynamic Frame Augmentation for Complex Video Understanding
May 26, 2026Peng Zhang, Guanghao Zhang, Wanggui He +10Multimodal Large Language Models Video Reasoning
Zhejiang University · Alibaba Group
Retrying vs Resampling in AI Control
May 25, 2026James Lucassen, Adam KaufmanAI Agent Safety AI Agent Monitoring
Redwood Research
Active Learning for Stochastic Contextual Linear Bandits
May 24, 2026Emma Brunskill, Ishani Karmarkar, Zhaoqi LiActive Learning Adaptive Sampling
Stanford University
Flow-Based Generative Modeling for Optimizing Sampling Policies in Compressed Sensing Applications
May 22, 2026Roman Pavelkin, Luis A. Zavala-Mondragon, Christiaan G. A. Viviers +1Flow Matching Image Reconstruction
Eindhoven University of Technology, Eindhoven
Instance-Optimal Estimation with Multiple LLM Judges on a Budget
May 22, 2026Junghyun Lee, Sanghwa Kim, Yassir Jedra +2Parameter Estimation LLM Evaluation
KAIST AI · ICL EEE · KTH EECS
Adaptive Measurement Allocation for Learning Kernelized SVMs Under Noisy Observations
May 21, 2026Artur MiroszewskiAdaptive Sampling Support Vector Machines
Φ-lab, European Space Agency (ESA/ESRIN), Frascati, Italy
MetaDNS: Enhancing Exploration in Discrete Neural Samplers via Well-Tempered Metadynamics
May 20, 2026Xiaochen Du, Juno Nam, Jaemoo Choi +7Free Energy Calculation Adaptive Sampling
Massachusetts Institute of Technology · Georgia Institute of Technology
Closed Loop Dynamic Driving Data Mixture for Real-Synthetic Co-Training
May 20, 2026Hongzhi Ruan, Pei Liu, Weiliang Ma +5Autonomous Driving Datasets Synthetic Data Augmentation
Li Auto · HKUST (GZ) · HKUST
SURF: Steering the Scalarization Weight to Uniformly Traverse the Pareto Front
May 20, 2026Liuyuan Jiang, Chentong Huang, Lisha ChenAdaptive Sampling Multi-Objective Optimization
Department of Electrical and Computer Engineering University of Rochester, Rochester, NY 14627
Active Context Selection Improves Simple Regret in Contextual Bandits
May 19, 2026Mohammad Shahverdikondori, Jalal Etesami, Negar KiyavashMulti-Armed Bandits Best-Arm Identification
College of Management of Technology, EPFL · Department of Computer Science, TU Munich
APS: Bias-Controlled Adaptive Prototype Simulation for Population-Scale LLM Agents
May 19, 2026Quan Zheng, Yan Gao, Shaobin He +6Human Behavior Simulation Adaptive Sampling
1Beijing Normal University · 2Zhongguancun Academy, Beijing, China · 3Zhongguancun Institute of Artificial Intelligence
SIREM: Speech-Informed MRI Reconstruction with Learned Sampling
May 18, 2026Md Hasan, Nyvenn Castro, Daiqi Liu +6Accelerated MRI Reconstruction Magnetic Resonance Imaging
1Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany · Institute of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany · 3Institut für Informationsverarbeitung, Leibniz Universität Hannover, Hannover, Germany +1
Curriculum Group Policy Optimization: Adaptive Sampling for Unleashing the Potential of Text-to-Image Generation
May 18, 2026Baoteng Li, Xianghao Zang, Xinran Wang +8Group Relative Policy Optimization Curriculum RL
School of Artificial Intelligence, Beijing University of Posts and Telecommunications1 · Beijing Key Laboratory of Multimodal Data Intelligent Perception and Governance3 · Institute of Artificial Intelligence (TeleAI), China Telecom2
Entropy Across the Bridge: Conditional-Marginal Discretization for Flow and Schrödinger Samplers
May 15, 2026Bruno Trentini, Dejan Stancevic, Michael M. Bronstein +2Flow Matching Schrödinger Bridges
NVIDIA Corporation, Santa Clara, CA, USA · University of Oxford, Dept. of Computer Science, Oxford, UK · Donders Institute for Brain, Cognition, and Behaviour, Radboud University, Nijmegen, NL +1
On the Power of Adaptivity for $\varepsilon$ -Best Arm Identification in Linear Bandits
May 15, 2026Arnab Maiti, Yunbei Xu, Kevin JamiesonMulti-Armed Bandits Best-Arm Identification
University of Washington · National University of Singapore
The Sample Complexity of Multiple Change Point Identification under Bandit Feedback
May 13, 2026Maximilian Graf, Victor ThuotSample Complexity Adaptive Sampling
INRAE, Mistea, Institut Agro, Univ Montpellier, Montpellier, France
Kernel-based guarantees for nonlinear parametric models in Bayesian optimization
May 13, 2026Rafael OliveiraBayesian Optimization Adaptive Sampling
The Commonwealth Scientific and Industrial Research Organisation (CSIRO) Sydney, Australia
NOVA: Fundamental Limits of Knowledge Discovery Through AI
May 12, 2026Salman Avestimehr, Ken Duffy, Muriel MédardAdaptive Sampling Autonomous Scientific Discovery
University of Southern California · Northeastern University · Massachusetts Institute of Technology
Learning U-Statistics with Active Inference
May 12, 2026Xiaoning Wang, Yuyang Huo, Liuhua Peng +1Active Inference U-Statistics
School of Statistics and Data Sciences, LPMC, KLM-DASR and LEBPS, Nankai University, Tianjin, China · School of Mathematics and Statistics, The University of Melbourne, Melbourne, Australia

Jun 1, 2026J/K move · Enter open · S save

ShaplEIG: Bayesian Experimental Design for Shapley Value Estimation

David Rundel, Fabian Fumagalli, Maximilian Muschalik, Bernd Bischl+1

Department of Statistics, LMU Munich, Munich, Germany · Munich Center for Machine Learning, Munich, Germany · Institute for Informatics, LMU Munich, Munich, Germany+2

Shapley Value Attribution Adaptive Sampling Bayesian Experimental Design

Open paper AskPDF arXiv

Shapley values are a principled attribution measure widely used in interpretable machine learning, but their exact computation scales exponentially with the number of players, motivating a wide range of approximation methods based on value function evaluations of sampled coalitions. This raises the question of whether approximation accuracy can be improved by adaptively selecting coalitions for evaluation based on previous evaluations. This is particularly relevant in settings where the value function is costly and the number of evaluations is severely limited, such as retraining-based feature importance, data valuation, and hyperparameter importance. For this purpose, we propose ShaplEIG, a Bayesian experimental design approach that approximates the expensive value function using a Gaussian process surrogate and adaptively selects coalitions based on their expected information gain about the Shapley values. By the linearity of the Shapley values in the value function, we show that the expected information gain is available in closed form. Furthermore, we propose an efficient computation scheme that reduces the complexity from exponential to polynomial in the number of players via elementary symmetric polynomials. In extensive experiments across diverse costly applications, our method consistently improves sample efficiency in the low-budget regime over state-of-the-art baselines.