{"total":35,"rows":[{"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":"2106.07171","title":"Examining and Combating Spurious Features under Distribution Shift","created":"2021-06-14","cited_by_count":65,"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":"2403.02187","title":"Mutual Information Estimation via Normalizing Flows","created":"2024-03-04","cited_by_count":22,"area":null},{"id":"2305.08013","title":"Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression","created":"2023-05-13","cited_by_count":19,"area":null},{"id":"2402.19465","title":"Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models","created":"2024-02-29","cited_by_count":18,"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":"2403.18494","title":"Learning in PINNs: Phase transition, diffusion equilibrium, and generalization","created":"2024-03-27","cited_by_count":13,"area":null},{"id":"2209.10438","title":"A Measure of the Complexity of Neural Representations based on Partial Information Decomposition","created":"2022-09-21","cited_by_count":11,"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":"2411.09894","title":"Free Lunch in Pathology Foundation Model: Task-specific Model Adaptation with Concept-Guided Feature Enhancement","created":"2024-11-15","cited_by_count":11,"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":"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":"2203.04109","title":"Explaining Classifiers by Constructing Familiar Concepts","created":"2022-03-07","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":"2209.12831","title":"Adaptation of Autoencoder for Sparsity Reduction From Clinical Notes Representation Learning","created":"2022-09-26","cited_by_count":4,"area":null},{"id":"2508.04753","title":"InfoQ: Mixed-Precision Quantization via Global Information Flow","created":"2025-08-06","cited_by_count":4,"area":null},{"id":"2509.20829","title":"Explaining Grokking and Information Bottleneck through Neural Collapse Emergence","created":"2025-09-25","cited_by_count":4,"area":null},{"id":"2509.26327","title":"A Generalized Information Bottleneck Theory of Deep Learning","created":"2025-09-30","cited_by_count":4,"area":null},{"id":"2509.02407","title":"Fisher information flow in artificial neural networks","created":"2025-09-02","cited_by_count":3,"area":null},{"id":"2312.06887","title":"Understanding and Leveraging the Learning Phases of Neural Networks","created":"2023-12-11","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":"2209.05082","title":"Bayesian Learning for Disparity Map Refinement for Semi-Dense Active Stereo Vision","created":"2022-09-12","cited_by_count":1,"area":null},{"id":"2404.01364","title":"Information Plane Analysis Visualization in Deep Learning via Transfer Entropy","created":"2024-04-01","cited_by_count":1,"area":null},{"id":"2503.06325","title":"Understanding the role of autoencoders for stiff dynamical systems using information theory","created":"2025-03-08","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":"2202.08299","title":"The learning phases in NN: From Fitting the Majority to Fitting a Few","created":"2022-02-16","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":"2310.19802","title":"Stochastic Thermodynamics of Learning Parametric Probabilistic Models","created":"2023-10-04","cited_by_count":0,"area":null},{"id":"2511.02584","title":"Redundancy Maximization as a Principle of Associative Memory Learning in Hopfield Networks","created":"2025-11-04","cited_by_count":0,"area":null},{"id":"2605.03636","title":"Information Plane Analysis of Binary Neural Networks","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2606.21593","title":"Geometric and Information Compression of Representations in Deep Learning","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2610.14290","title":"Layer-wise Input Recoverability in Deep Neural Networks","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.16660","title":"Compression Through Time: An Interplay of Separability, Stationarity and Capacity","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}