Information Bottleneck

Also known as IB

Ask about this topic

Overview

Information Bottleneck methods seek compact representations that preserve information relevant to a task while discarding irrelevant details. Common approaches include variational and conditional bottlenecks, mutual-information or rate-distortion objectives, and contrastive or structured regularizers. They are used in learning robust features, protecting privacy, explaining predictions, and limiting communication or memory in agents and multimodal systems. A central challenge is choosing and optimizing the compression level: too little compression retains nuisance information, while too much removes evidence needed for the task, and the right balance depends on the setting.

Latest papers

CardsList

56 papers10 papers in the last four weeks, up 150% on the four weeks before. 0.1% of all new papers.

  1. Optimal Multitask Representations Under a Rate Constraint: An Information Bottleneck Analysis

    Oct 21, 2026Nicholas Stiles, Gregory W. WornellRepresentation LearningInformation Bottleneck

    Massachusetts Institute of Technology

  2. SICAF: Time-Varying Focus Bottleneck for Self-Supervised Event-Based Optical Flow with Spiking Neural Network

    Oct 21, 2026Shuangming Yang, Qing He, Shangqi Guo +1Event-Based Optical FlowSpiking Neural Networks

    Tianjin University, Tianjin, China · Tsinghua University, Beijing, China · Xi’an Jiaotong University, Xi’an, China

  3. Robust Representation Learning for Spiking Neural Networks based on Conditional Information Bottleneck

    Oct 20, 2026Yuli Zha, Wang Fan, Yixiao Dai +5Spiking Neural NetworksNeural Network Robustness

    College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, 200433, China · Institute of Big Data, Fudan University, Shanghai, 200433, China

  4. Quasi-Binarized Autoencoders: An Architecture-Independent Information Bottleneck for Medical Image Anomaly Detection

    Oct 7, 2026Shouhei Hanaoka, Takahiro Nakao, Atsushi Takamatsu +2Medical Image Anomaly DetectionUnsupervised Anomaly Detection

    Department of Radiology, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan · Department of Computational Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan · Department of Radiology, Kanazawa University Hospital, 13-1 Takara-machi, Kanazawa, Ishikawa, 920-8641, Japan

  5. IronMan: Information-Constrained Video-Action Learning for Robot Manipulation

    Oct 6, 2026Yuanshuo Zhang, Wenzhe Zhao, Zixing Lei +2Information BottleneckGeneralization in Robotic Manipulation

    Shanghai Jiao Tong University · Joy Future Academy, JD

  6. On the Cardinality of Optimal Representations in the Binary-Source Information Bottleneck

    Oct 5, 2026Dier Tang, Jun ChenInformation BottleneckMutual Information

    Department of Mathematics, The University of Hong Kong · Electrical and Computer Engineering, McMaster University

  7. Rethinking the Information Bottleneck: Structured Decomposition under Label-Induced Partitions

    Oct 1, 2026Jingyao Zhang, Yuxuan Li, Lu Han +2Information BottleneckInvariant Representation Learning

    School of Computer Science, The University of Sydney Sydney, NSW 2006, Australia

  8. Mutual Information Constrained Chernoff Bottleneck

    Sep 29, 2026Dier Tang, Guangyue HanInformation Bottleneck

    Department of Mathematics, The University of Hong Kong

  9. Information Bottleneck-Guided Adaptive Hypergraph Transformer for Brain Disease Diagnosis

    Sep 29, 2026Jingxi Feng, Xudong Chen, Yifan Zhang +5Medical DiagnosisInformation Bottleneck

  10. Attention-based Hierarchical Variational Information Bottleneck for Robust Multi-Agent Communication under Variable Bandwidth

    Sep 28, 2026Lukas Koch Vindbjerg, Qi Zhang, Yury Brodskiy +1Information BottleneckMulti-Agent Communication

    Department of Electrical and Computer Engineering, Aarhus University, Aarhus, Denmark · EIVA a/s, Denmark · DIGIT, Aarhus University, Aarhus, Denmark

  11. SGWIB:Sliced Gromov-Wasserstein Information Bottleneck for Video Highlight Detection

    Sep 12, 2026Hanjuan Huang, Yung-Chieh Yeh, Hsing-Kuo PaoTemporal Video UnderstandingInformation Bottleneck

    Key Laboratory of Agricultural Machinery Intelligent Control and Manufacturing of Fujian Province University, College of Mechanical and Electrical Engineering, Wuyi University, Wuyishan 354300, China · National Taiwan University of Science and Technology, No. 43, Sec. 4, Keelung Rd., Taipei, Taiwan

  12. Beyond Argmax: A Mechanistic Study of Semantic Retention in Frozen Foundation-Model Composition for Generalized Few-Shot 3D Segmentation

    Sep 10, 2026Silas Kwabla Gah, Ebenezer Owusu3D Foundation ModelsEnsemble Learning

    Department of Computer Science University of Ghana, Legon

  13. Learning Manipulation-Sufficient Representations via Outcome Bottlenecks

    Sep 2, 2026Md Selim Sarowar, Sungho KimRepresentation LearningRobotics

    Department of Electronics Engineering, Yeungnam University, Gyeongsan 38541, Republic of Korea.

  14. Synergistic Information Disentanglement for Omni-modal Slide Representation Learning in Computational Pathology

    Sep 2, 2026Mingxin Liu, Chengfei Cai, Anwen Lu +5Multimodal SSLMedical Image Representation Learning

    Jiangsu Key Laboratory of Intelligent Medical Image Computing, School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing, China · Jiangsu Key Laboratory of Intelligent Drug Screening and Repositioning, College of Information Engineering, Taizhou University, Taizhou, China · College of Bioinformatics Science and Technology, Harbin Medical University, Harbin, China

  15. Towards A Unified Information Bottleneck Framework for Time Series Explanations

    Aug 26, 2026Xu Zheng, Zichuan Liu, Zhuomin Chen +7Explainable Time Series ForecastingExplainable Artificial Intelligence

    Florida International University · Carnegie Mellon University · University of Houston +2

  16. GRIP: Grounded Reasoning via Information-Restricted Premises

    Aug 17, 2026Lirui TengRetrieval-Augmented GenerationLLM Grounding

    University of Waterloo, Waterloo ON, Canada

  17. Information Bottleneck under Perfect Privacy

    Aug 11, 2026Junle Zhong, Mohamad Assaad, Sreejith SreekumarInformation BottleneckPrivacy-Preserving ML

    Laboratoire des Signaux et Syst`emes (L2S), CNRS, CentraleSup´elec, Universit´e Paris-Saclay, 91190 Gif-sur-Yvette, France

  18. Information Bottleneck Learning for Faithful Time Series Forecasting Explanations

    Jul 30, 2026Xu Zheng, Wei Cheng, Zhuomin Chen +3Multivariate Time Series ForecastingExplainable Time Series Forecasting

    Florida International University, Miami, FL, USA · NEC Laboratories America, Princeton, NJ, USA · University of Houston, Houston, TX, USA +1

  19. Towards Dual-Brain Minimal Sufficient Representation for Vision-Language Navigation

    Jul 25, 2026Yihao Wu, Chenyi Xu, Liqi Yan +6Representation LearningInformation Bottleneck

    1Hangzhou Dianzi University · University of Zurich · University of Exeter

  20. Indexing: the Beginning and the End

    Jul 24, 2026Alexander Kozachinskiy, Vicente Opazo, Felipe UrrutiaInformation BottleneckLinear Attention

    CENIA · Pontifical Catholic University of Chile

  21. Rethinking Layer-Wise Information Allocation for Vision Foundation Model Adaptation

    Jul 24, 2026Yuqi Li, Xi Xiao, Yunbei Zhang +6Information BottleneckVision Foundation Model Adaptation

    City College of New York, CUNY · New York, NY, USA · University of Alabama at Birmingham +11

  22. External Clustering Validation by the Homogeneity-Parsimony Trade-off

    Jul 22, 2026Andreas Tiffeau-MayerClusteringInformation Bottleneck

    Division of Infection and Immunity & Institute for the Physics of Living Systems, University College London

  23. When Do Multi-Agent Systems Help? An Information Bottleneck Perspective

    Jul 17, 2026Wendi Yu, Lianhao Zhou, Xiangjue Dong +6Multi-Agent LLM SystemsInformation Bottleneck

    Department of Computer Science & Engineering, Texas A&M University · Department of Electrical & Computer Engineering, Texas A&M University · Computing and Data Sciences Directorate, Brookhaven National Laboratory

  24. Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content

    Jul 17, 2026Ingo Ziegler, Martin Krebs, Desmond ElliottInformation BottleneckTokenization in Language Models

    Department of Computer Science, University of Copenhagen

  25. The SIGReg Objective as Variational Free Energy: A Theoretical Active-Inference Account of JEPA World Models

    Jul 15, 2026Fabio Arnez, Alexandra Gomez-VillaWorld Model LearningActive Inference

    Université Paris-Saclay, CEA, List F-91120, Palaiseau, France · Computer Vision Center Barcelona, Spain

  26. Emergent Generalization by Representation Learning in Artificial Neural Networks

    Jul 11, 2026Hardik Rajpal, Dan GoodmanNeural Network GeneralizationRepresentation Learning

    1I-X Centre for AI in Science, Imperial College London, W12 0BZ, UK · Department of Electrical and Electronic Engineering, Imperial College London, SW7 2AZ, UK

  27. Domain Generalization via Text-Anchored Information Bottleneck

    Jul 2, 2026Eunyi Lyou, Yunjeong Choi, Junho Lee +1VLM RobustnessInformation Bottleneck

    Seoul National University, Seoul, Republic of Korea

  28. Informational Frustration in Neural Manifolds: Shannon Bottlenecks and the Limits of Learnability

    Jun 29, 2026Srinivasa Rao P., Vangmayi P ReddyStatistical Physics of LearningNeural Network Generalization

    Curlvee Technolabs, India, Former Scientist, C-DAC · Former Scientist, C-DAC · Indian Institute of Technology Madras, India

  29. What Fits (Into Few Tokens) Doesn't Overfit: Compression and Generalization in ML Research Agents

    Jun 9, 2026Martin Andres Bertran, Aaron Roth, Zhiwei Steven WuMinimum Description LengthBenchmark Contamination

    Amazon Responsible AI · University of Pennsylvania · Carnegie Mellon University

  30. The Bioelectrical Information Theory: Investigating the theoretical compression limit of bioelectrical signals under artificial intelligence

    Jun 7, 2026Jiawen Zou, Bo YanBrain-Computer InterfacesInformation Bottleneck

    College of Computer Science and Artificial Intelligence, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai 200433, P.R. China