{"total":30,"rows":[{"id":"2112.08903","title":"Graph Structure Learning with Variational Information Bottleneck","created":"2021-12-16","cited_by_count":81,"area":null},{"id":"2110.06530","title":"Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation","created":"2021-10-13","cited_by_count":65,"area":null},{"id":"2106.10800","title":"Lossy Compression for Lossless Prediction","created":"2021-06-21","cited_by_count":52,"area":null},{"id":"2201.00057","title":"Optimal Representations for Covariate Shift","created":"2021-12-31","cited_by_count":51,"area":null},{"id":"2109.12909","title":"Compressive Visual Representations","created":"2021-09-27","cited_by_count":41,"area":null},{"id":"2209.06235","title":"Improving Self-Supervised Learning by Characterizing Idealized Representations","created":"2022-09-13","cited_by_count":34,"area":null},{"id":"2304.01434","title":"VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution","created":"2023-04-04","cited_by_count":17,"area":null},{"id":"2205.12239","title":"Gacs-Korner Common Information Variational Autoencoder","created":"2022-05-24","cited_by_count":12,"area":null},{"id":"2402.03254","title":"Minimum Description Length and Generalization Guarantees for Representation Learning","created":"2024-02-05","cited_by_count":11,"area":null},{"id":"2302.10888","title":"Data-Efficient Protein 3D Geometric Pretraining via Refinement of Diffused Protein Structure Decoy","created":"2023-02-05","cited_by_count":10,"area":null},{"id":"2404.17951","title":"Cauchy-Schwarz Divergence Information Bottleneck for Regression","created":"2024-04-27","cited_by_count":9,"area":null},{"id":"2105.13977","title":"Perturbation Theory for the Information Bottleneck","created":"2021-05-28","cited_by_count":6,"area":null},{"id":"2205.14539","title":"Improving VAE-based Representation Learning","created":"2022-05-28","cited_by_count":6,"area":null},{"id":"2302.03068","title":"Evaluating Self-Supervised Learning via Risk Decomposition","created":"2023-02-06","cited_by_count":6,"area":null},{"id":"2401.15935","title":"MLEM: Generative and Contrastive Learning as Distinct Modalities for Event Sequences","created":"2024-01-29","cited_by_count":6,"area":null},{"id":"2204.08226","title":"Empirical Evaluation and Theoretical Analysis for Representation Learning: A Survey","created":"2022-04-18","cited_by_count":5,"area":null},{"id":"2304.14618","title":"Recognizable Information Bottleneck","created":"2023-04-28","cited_by_count":5,"area":null},{"id":"2308.15856","title":"Domain Generalization without Excess Empirical Risk","created":"2023-08-30","cited_by_count":3,"area":null},{"id":"2512.03528","title":"Multi-Agent Reinforcement Learning with Communication-Constrained Priors","created":"2025-12-03","cited_by_count":3,"area":null},{"id":"2210.02989","title":"SynBench: Task-Agnostic Benchmarking of Pretrained Representations using Synthetic Data","created":"2022-10-06","cited_by_count":2,"area":null},{"id":"2502.15540","title":"Generalization Guarantees for Representation Learning via Data-Dependent Gaussian Mixture Priors","created":"2025-02-21","cited_by_count":2,"area":null},{"id":"2311.03955","title":"Elastic Information Bottleneck","created":"2023-11-07","cited_by_count":1,"area":null},{"id":"2403.06971","title":"A representation-learning game for classes of prediction tasks","created":"2024-03-11","cited_by_count":1,"area":null},{"id":"2504.18455","title":"Multiview Representation Learning via Distributed Joint Latent Space Structuring","created":"2025-04-25","cited_by_count":1,"area":null},{"id":"2509.14498","title":"Data coarse graining can improve model performance","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2207.07174","title":"Attribute Graphs Underlying Molecular Generative Models: Path to Learning with Limited Data","created":"2022-07-14","cited_by_count":0,"area":null},{"id":"2606.09922","title":"The Bioelectrical Information Theory: Investigating the theoretical compression limit of bioelectrical signals under artificial intelligence","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2609.11132","title":"How Wrong Can a Good Predictor Be? Diverging Updates with Vanishing Predictive KL","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.26207","title":"RCShift: Certifying When Partial Linkage Suffices for Finite-Sample Decisions","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2610.07906","title":"Isotropic Yet Undecodable: The Sequential Content-Sufficiency Gap in Latent-Predictive Text Representations","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}