{"total":43,"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":"2106.03443","title":"Causal Influence Detection for Improving Efficiency in Reinforcement Learning","created":"2021-06-07","cited_by_count":71,"area":null},{"id":"2104.02862","title":"Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identification","created":"2021-04-07","cited_by_count":50,"area":null},{"id":"2306.11078","title":"Beyond Normal: On the Evaluation of Mutual Information Estimators","created":"2023-06-19","cited_by_count":37,"area":null},{"id":"2310.09031","title":"MINDE: Mutual Information Neural Diffusion Estimation","created":"2023-10-13","cited_by_count":31,"area":null},{"id":"2110.02501","title":"On the Surrogate Gap between Contrastive and Supervised Losses","created":"2021-10-06","cited_by_count":25,"area":null},{"id":"2107.01152","title":"Simpler, Faster, Stronger: Breaking The log-K Curse On Contrastive Learners With FlatNCE","created":"2021-07-02","cited_by_count":22,"area":null},{"id":"2409.02732","title":"Approximating mutual information of high-dimensional variables using learned representations","created":"2024-09-03","cited_by_count":21,"area":null},{"id":"2107.01131","title":"Tight Mutual Information Estimation With Contrastive Fenchel-Legendre Optimization","created":"2021-07-02","cited_by_count":18,"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":"2302.01915","title":"Sample Complexity of Probability Divergences under Group Symmetry","created":"2023-02-03","cited_by_count":14,"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":"2207.02970","title":"Network Binarization via Contrastive Learning","created":"2022-07-06","cited_by_count":12,"area":null},{"id":"2312.00194","title":"Robust Concept Erasure via Kernelized Rate-Distortion Maximization","created":"2023-11-30","cited_by_count":11,"area":null},{"id":"2410.10924","title":"A Benchmark Suite for Evaluating Neural Mutual Information Estimators on Unstructured Datasets","created":"2024-10-14","cited_by_count":10,"area":null},{"id":"2105.02629","title":"Bird's Eye: Probing for Linguistic Graph Structures with a Simple Information-Theoretic Approach","created":"2021-05-06","cited_by_count":9,"area":null},{"id":"2503.04725","title":"L$^2$M: Mutual Information Scaling Law for Long-Context Language Modeling","created":"2025-03-06","cited_by_count":9,"area":null},{"id":"2211.04928","title":"miCSE: Mutual Information Contrastive Learning for Low-shot Sentence Embeddings","created":"2022-11-09","cited_by_count":7,"area":null},{"id":"2306.00608","title":"On the Effectiveness of Hybrid Mutual Information Estimation","created":"2023-06-01","cited_by_count":7,"area":null},{"id":"2102.13182","title":"MIND: Inductive Mutual Information Estimation, A Convex Maximum-Entropy Copula Approach","created":"2021-02-25","cited_by_count":6,"area":null},{"id":"2111.06676","title":"A Reverse Jensen Inequality Result with Application to Mutual Information Estimation","created":"2021-11-12","cited_by_count":5,"area":null},{"id":"2211.00024","title":"A robust estimator of mutual information for deep learning interpretability","created":"2022-10-31","cited_by_count":4,"area":null},{"id":"2407.13841","title":"Many Perception Tasks are Highly Redundant Functions of their Input Data","created":"2024-07-18","cited_by_count":4,"area":null},{"id":"2307.15830","title":"A Distance Correlation-Based Approach to Characterize the Effectiveness of Recurrent Neural Networks for Time Series Forecasting","created":"2023-07-28","cited_by_count":3,"area":null},{"id":"2202.09875","title":"Trying to Outrun Causality with Machine Learning: Limitations of Model Explainability Techniques for Identifying Predictive Variables","created":"2022-02-20","cited_by_count":2,"area":null},{"id":"2308.15704","title":"Towards a Rigorous Analysis of Mutual Information in Contrastive Learning","created":"2023-08-30","cited_by_count":2,"area":null},{"id":"2502.19183","title":"INFO-SEDD: Continuous Time Markov Chains as Scalable Information Metrics Estimators","created":"2025-02-26","cited_by_count":2,"area":null},{"id":"2506.00330","title":"Accurate Estimation of Mutual Information in High Dimensional Data","created":"2025-05-31","cited_by_count":2,"area":null},{"id":"2510.22767","title":"TELL-TALE: Task Efficient LLMs with Task Aware Layer Elimination","created":"2025-10-26","cited_by_count":2,"area":null},{"id":"2605.25773","title":"Efficient Benchmarking Is Just Feature Selection and Multiple Regression","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2307.12716","title":"Safety Performance of Neural Networks in the Presence of Covariate Shift","created":"2023-07-24","cited_by_count":1,"area":null},{"id":"2510.21686","title":"Multimodal Datasets with Controllable Mutual Information","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2603.27074","title":"Forecastability as an Information-Theoretic Limit on Prediction","created":"2026-03-28","cited_by_count":1,"area":null},{"id":"2106.09330","title":"A Simple Generative Network","created":"2021-06-17","cited_by_count":0,"area":null},{"id":"2402.06295","title":"Multimodal Interpretable Data-Driven Models for Early Prediction of Antimicrobial Multidrug Resistance Using Multivariate Time-Series","created":"2024-02-09","cited_by_count":0,"area":null},{"id":"2404.05043","title":"Optimizing Privacy and Utility Tradeoffs for Group Interests Through Harmonization","created":"2024-04-07","cited_by_count":0,"area":null},{"id":"2408.09377","title":"Mutual Information Multinomial Estimation","created":"2024-08-18","cited_by_count":0,"area":null},{"id":"2410.10082","title":"fastHDMI: Fast Mutual Information Estimation for High-Dimensional Data","created":"2024-10-14","cited_by_count":0,"area":null},{"id":"2508.16509","title":"ML-PWS: Estimating the Mutual Information Between Experimental Time Series Using Neural Networks","created":"2025-08-22","cited_by_count":0,"area":null},{"id":"2511.13602","title":"Nonparametric Estimation of Joint Entropy via Partitioned Sample-Spacing","created":"2025-11-17","cited_by_count":0,"area":null},{"id":"2605.14738","title":"TAPIOCA: Why Task- Aware Pruning Improves OOD model Capability","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2607.27710","title":"NMINE: Normalized Mutual Information Neural Estimation","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2609.34962","title":"ALICE: In-context, Zero-shot, Mutual Information Estimation","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}