{"total":33,"rows":[{"id":"2305.18887","title":"How Does Information Bottleneck Help Deep Learning?","created":"2023-05-30","cited_by_count":93,"area":null},{"id":"2303.00633","title":"An Information-Theoretic Perspective on Variance-Invariance-Covariance Regularization","created":"2023-03-01","cited_by_count":25,"area":null},{"id":"2202.06618","title":"A Differential Entropy Estimator for Training Neural Networks","created":"2022-02-14","cited_by_count":20,"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":"2207.10081","title":"What Do We Maximize in Self-Supervised Learning?","created":"2022-07-20","cited_by_count":15,"area":null},{"id":"2312.04823","title":"Assessing Neural Network Representations During Training Using Noise-Resilient Diffusion Spectral Entropy","created":"2023-12-04","cited_by_count":13,"area":null},{"id":"2404.17951","title":"Cauchy-Schwarz Divergence Information Bottleneck for Regression","created":"2024-04-27","cited_by_count":9,"area":null},{"id":"2206.02435","title":"Tackling covariate shift with node-based Bayesian neural networks","created":"2022-06-06","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":"2310.10240","title":"On the Properties and Estimation of Pointwise Mutual Information Profiles","created":"2023-10-16","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":"2201.01034","title":"Uncovering the Over-smoothing Challenge in Image Super-Resolution: Entropy-based Quantification and Contrastive Optimization","created":"2022-01-04","cited_by_count":6,"area":null},{"id":"2306.08424","title":"Selective Concept Models: Permitting Stakeholder Customisation at Test-Time","created":"2023-06-14","cited_by_count":6,"area":null},{"id":"2408.05496","title":"Variational Inference Failures Under Model Symmetries: Permutation Invariant Posteriors for Bayesian Neural Networks","created":"2024-08-10","cited_by_count":6,"area":null},{"id":"2103.10176","title":"Maximum Entropy Reinforcement Learning with Mixture Policies","created":"2021-03-18","cited_by_count":4,"area":null},{"id":"2502.08365","title":"Towards Principled Unsupervised Multi-Agent Reinforcement Learning","created":"2025-02-12","cited_by_count":4,"area":null},{"id":"2106.03213","title":"On Local Aggregation in Heterophilic Graphs","created":"2021-06-06","cited_by_count":3,"area":null},{"id":"2110.06057","title":"Gated Information Bottleneck for Generalization in Sequential Environments","created":"2021-10-12","cited_by_count":3,"area":null},{"id":"2110.09618","title":"Interpolating between sampling and variational inference with infinite stochastic mixtures","created":"2021-10-18","cited_by_count":3,"area":null},{"id":"2412.08222","title":"Structured IB: Improving Information Bottleneck with Structured Feature Learning","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2201.09069","title":"Neuronal Correlation: a Central Concept in Neural Network","created":"2022-01-22","cited_by_count":2,"area":null},{"id":"2205.01940","title":"Towards Theoretical Analysis of Transformation Complexity of ReLU DNNs","created":"2022-05-04","cited_by_count":2,"area":null},{"id":"2405.21042","title":"Comparing the information content of probabilistic representation spaces","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2506.09452","title":"Learning Obfuscations Of LLM Embedding Sequences: Stained Glass Transform","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2105.07181","title":"Drill the Cork of Information Bottleneck by Inputting the Most Important Data","created":"2021-05-15","cited_by_count":1,"area":null},{"id":"2308.13498","title":"Efficient Epistemic Uncertainty Estimation in Regression Ensemble Models Using Pairwise-Distance Estimators","created":"2023-08-25","cited_by_count":1,"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":"2101.08427","title":"Analysis of Information Flow Through U-Nets","created":"2021-01-21","cited_by_count":0,"area":null},{"id":"2203.16887","title":"Mutual information estimation for graph convolutional neural networks","created":"2022-03-31","cited_by_count":0,"area":null},{"id":"2207.05756","title":"Exploring Adversarial Examples and Adversarial Robustness of Convolutional Neural Networks by Mutual Information","created":"2022-07-12","cited_by_count":0,"area":null},{"id":"2510.00734","title":"Approximation of differential entropy in Bayesian optimal experimental design","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2610.12904","title":"GIST: Generator-state-Informed Supervision for Tabular Foundation Models","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.14012","title":"Perfect Reconstruction Cannot Show Whether Two Codebooks on a VAE's Latent Space Agree","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}