{"total":14,"rows":[{"id":"2305.18887","title":"How Does Information Bottleneck Help Deep Learning?","created":"2023-05-30","cited_by_count":93,"area":null},{"id":"2304.09355","title":"To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Review","created":"2023-04-19","cited_by_count":72,"area":null},{"id":"2310.13620","title":"Bridging Information-Theoretic and Geometric Compression in Language Models","created":"2023-10-20","cited_by_count":26,"area":null},{"id":"2106.12912","title":"Information Bottleneck: Exact Analysis of (Quantized) Neural Networks","created":"2021-06-24","cited_by_count":15,"area":null},{"id":"2105.03705","title":"Understanding Neural Networks with Logarithm Determinant Entropy Estimator","created":"2021-05-08","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":"2402.09050","title":"End-to-End Training Induces Information Bottleneck through Layer-Role Differentiation: A Comparative Analysis with Layer-wise Training","created":"2024-02-14","cited_by_count":8,"area":null},{"id":"2202.10716","title":"HRel: Filter Pruning based on High Relevance between Activation Maps and Class Labels","created":"2022-02-22","cited_by_count":7,"area":null},{"id":"2412.07169","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","created":"2024-12-10","cited_by_count":7,"area":null},{"id":"2102.07402","title":"Information flows of diverse autoencoders","created":"2021-02-15","cited_by_count":6,"area":null},{"id":"2207.09408","title":"Bounding generalization error with input compression: An empirical study with infinite-width networks","created":"2022-07-19","cited_by_count":4,"area":null},{"id":"2309.02787","title":"Dynamic Encoding and Decoding of Information for Split Learning in Mobile-Edge Computing: Leveraging Information Bottleneck Theory","created":"2023-09-06","cited_by_count":1,"area":null},{"id":"2109.09016","title":"The Unreasonable Effectiveness of the Final Batch Normalization Layer","created":"2021-09-18","cited_by_count":0,"area":null},{"id":"2510.27651","title":"Information-Theoretic Greedy Layer-wise Training for Traffic Sign Recognition","created":"2025-10-31","cited_by_count":0,"area":null}],"next_cursor":null}