{"total":128,"rows":[{"id":"2101.04702","title":"Cross-Modal Contrastive Learning for Text-to-Image Generation","created":"2021-01-12","cited_by_count":259,"area":null},{"id":"2203.13457","title":"Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap","created":"2022-03-25","cited_by_count":105,"area":null},{"id":"2306.05268","title":"Factorized Contrastive Learning: Going Beyond Multi-view Redundancy","created":"2023-06-08","cited_by_count":75,"area":null},{"id":"2203.07004","title":"Rethinking Minimal Sufficient Representation in Contrastive Learning","created":"2022-03-14","cited_by_count":69,"area":null},{"id":"2111.02329","title":"Implicit Deep Adaptive Design: Policy-Based Experimental Design without Likelihoods","created":"2021-11-03","cited_by_count":61,"area":null},{"id":"2111.11010","title":"Density Ratio Estimation via Infinitesimal Classification","created":"2021-11-22","cited_by_count":61,"area":null},{"id":"2101.05544","title":"DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation","created":"2021-01-14","cited_by_count":48,"area":null},{"id":"2102.05113","title":"Negative Data Augmentation","created":"2021-02-09","cited_by_count":46,"area":null},{"id":"2110.02719","title":"The Information Geometry of Unsupervised Reinforcement Learning","created":"2021-10-06","cited_by_count":37,"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":"2107.02212","title":"Featurized Density Ratio Estimation","created":"2021-07-05","cited_by_count":33,"area":null},{"id":"2310.09031","title":"MINDE: Mutual Information Neural Diffusion Estimation","created":"2023-10-13","cited_by_count":31,"area":null},{"id":"2106.07278","title":"Which Mutual-Information Representation Learning Objectives are Sufficient for Control?","created":"2021-06-14","cited_by_count":29,"area":null},{"id":"2103.11275","title":"Self-supervised Representation Learning with Relative Predictive Coding","created":"2021-03-21","cited_by_count":28,"area":null},{"id":"2103.04537","title":"Multimodal Representation Learning via Maximization of Local Mutual Information","created":"2021-03-08","cited_by_count":27,"area":null},{"id":"2105.04379","title":"Gradient-based Bayesian Experimental Design for Implicit Models using Mutual Information Lower Bounds","created":"2021-05-10","cited_by_count":27,"area":null},{"id":"2106.13401","title":"Decomposed Mutual Information Estimation for Contrastive Representation Learning","created":"2021-06-25","cited_by_count":25,"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":"2107.11635","title":"Clustering by Maximizing Mutual Information Across Views","created":"2021-07-24","cited_by_count":23,"area":null},{"id":"2408.04591","title":"HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain Shifts","created":"2024-08-08","cited_by_count":23,"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":"2403.02187","title":"Mutual Information Estimation via Normalizing Flows","created":"2024-03-04","cited_by_count":22,"area":null},{"id":"2306.03301","title":"Estimating Conditional Mutual Information for Dynamic Feature Selection","created":"2023-06-05","cited_by_count":21,"area":null},{"id":"2310.11048","title":"Understanding Contrastive Learning via Distributionally Robust Optimization","created":"2023-10-17","cited_by_count":21,"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":"2202.06618","title":"A Differential Entropy Estimator for Training Neural Networks","created":"2022-02-14","cited_by_count":20,"area":null},{"id":"2207.09176","title":"Self-Supervision Can Be a Good Few-Shot Learner","created":"2022-07-19","cited_by_count":19,"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":"2305.20025","title":"Mutual Information Estimation via $f$-Divergence and Data Derangements","created":"2023-05-31","cited_by_count":17,"area":null},{"id":"2203.04272","title":"Policy-Based Bayesian Experimental Design for Non-Differentiable Implicit Models","created":"2022-03-08","cited_by_count":16,"area":null},{"id":"2109.00922","title":"Improving Multimodal fusion via Mutual Dependency Maximisation","created":"2021-08-31","cited_by_count":15,"area":null},{"id":"2103.04813","title":"Boosting Semi-supervised Image Segmentation with Global and Local Mutual Information Regularization","created":"2021-03-08","cited_by_count":14,"area":null},{"id":"2205.03589","title":"Learning Disentangled Textual Representations via Statistical Measures of Similarity","created":"2022-05-07","cited_by_count":14,"area":null},{"id":"2206.00006","title":"COIN: Co-Cluster Infomax for Bipartite Graphs","created":"2022-05-31","cited_by_count":14,"area":null},{"id":"2211.15353","title":"Copula Density Neural Estimation","created":"2022-11-25","cited_by_count":13,"area":null},{"id":"2502.02300","title":"Density Ratio Estimation with Conditional Probability Paths","created":"2025-02-04","cited_by_count":13,"area":null},{"id":"2302.05428","title":"STERLING: Synergistic Representation Learning on Bipartite Graphs","created":"2023-01-25","cited_by_count":12,"area":null},{"id":"2106.00252","title":"Information-Theoretic Analysis of Epistemic Uncertainty in Bayesian Meta-learning","created":"2021-06-01","cited_by_count":10,"area":null},{"id":"2107.06456","title":"AID-Purifier: A Light Auxiliary Network for Boosting Adversarial Defense","created":"2021-07-14","cited_by_count":10,"area":null},{"id":"2309.16200","title":"Max-Sliced Mutual Information","created":"2023-09-28","cited_by_count":10,"area":null},{"id":"2402.05132","title":"TexShape: Information Theoretic Sentence Embedding for Language Models","created":"2024-02-05","cited_by_count":10,"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":"2208.06270","title":"RenyiCL: Contrastive Representation Learning with Skew Renyi Divergence","created":"2022-08-12","cited_by_count":8,"area":null},{"id":"2302.10701","title":"Scalable Infomin Learning","created":"2023-02-21","cited_by_count":8,"area":null},{"id":"2307.05906","title":"Mini-Batch Optimization of Contrastive Loss","created":"2023-07-12","cited_by_count":8,"area":null},{"id":"2401.01268","title":"$f$-Divergence Based Classification: Beyond the Use of Cross-Entropy","created":"2024-01-02","cited_by_count":8,"area":null},{"id":"2409.07594","title":"Automated Discovery of Pairwise Interactions from Unstructured Data","created":"2024-09-11","cited_by_count":8,"area":null},{"id":"2103.08026","title":"A Scalable Gradient-Free Method for Bayesian Experimental Design with Implicit Models","created":"2021-03-14","cited_by_count":7,"area":null},{"id":"2109.14688","title":"Reliable Estimation of KL Divergence using a Discriminator in Reproducing Kernel Hilbert Space","created":"2021-09-29","cited_by_count":7,"area":null},{"id":"2206.12292","title":"InfoAT: Improving Adversarial Training Using the Information Bottleneck Principle","created":"2022-06-23","cited_by_count":7,"area":null},{"id":"2210.04974","title":"Function-space regularized R\\'enyi divergences","created":"2022-10-10","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":"2307.04317","title":"Text Descriptions are Compressive and Invariant Representations for Visual Learning","created":"2023-07-10","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":"2410.04959","title":"Collapse-Proof Non-Contrastive Self-Supervised Learning","created":"2024-10-07","cited_by_count":7,"area":null},{"id":"2502.01383","title":"InfoBridge: Mutual Information estimation via Bridge Matching","created":"2025-02-03","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":"2212.13425","title":"GEDI: GEnerative and DIscriminative Training for Self-Supervised Learning","created":"2022-12-27","cited_by_count":6,"area":null},{"id":"2309.07200","title":"Latent Representation and Simulation of Markov Processes via Time-Lagged Information Bottleneck","created":"2023-09-13","cited_by_count":6,"area":null},{"id":"2402.02444","title":"BECLR: Batch Enhanced Contrastive Few-Shot Learning","created":"2024-02-04","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":"2503.20098","title":"Fundamental Limits of Perfect Concept Erasure","created":"2025-03-25","cited_by_count":6,"area":null},{"id":"2205.13300","title":"Federated Non-negative Matrix Factorization for Short Texts Topic Modeling with Mutual Information","created":"2022-05-26","cited_by_count":5,"area":null},{"id":"2208.12352","title":"OOD-Probe: A Neural Interpretation of Out-of-Domain Generalization","created":"2022-08-25","cited_by_count":5,"area":null},{"id":"2308.09888","title":"On Estimating the Gradient of the Expected Information Gain in Bayesian Experimental Design","created":"2023-08-19","cited_by_count":5,"area":null},{"id":"2510.04417","title":"Partial Information Decomposition via Normalizing Flows in Latent Gaussian Distributions","created":"2025-10-06","cited_by_count":5,"area":null},{"id":"2111.07401","title":"Neural Capacity Estimators: How Reliable Are They?","created":"2021-11-14","cited_by_count":4,"area":null},{"id":"2112.05787","title":"Representation Learning for Conversational Data using Discourse Mutual Information Maximization","created":"2021-12-04","cited_by_count":4,"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":"2510.20644","title":"Connecting Jensen-Shannon and Kullback-Leibler Divergences: A New Bound for Representation Learning","created":"2025-10-23","cited_by_count":4,"area":null},{"id":"2510.20968","title":"Neural Mutual Information Estimation with Vector Copulas","created":"2025-10-23","cited_by_count":4,"area":null},{"id":"2110.00385","title":"Neural Dependency Coding inspired Multimodal Fusion","created":"2021-09-28","cited_by_count":3,"area":null},{"id":"2110.08931","title":"Quantifying the Task-Specific Information in Text-Based Classifications","created":"2021-10-17","cited_by_count":3,"area":null},{"id":"2204.03030","title":"Statistical Model Criticism of Variational Auto-Encoders","created":"2022-04-06","cited_by_count":3,"area":null},{"id":"2205.07061","title":"MIND: Maximum Mutual Information Based Neural Decoder","created":"2022-05-14","cited_by_count":3,"area":null},{"id":"2410.22784","title":"Contrastive Learning and Adversarial Disentanglement for Privacy-Aware Task-Oriented Semantic Communication","created":"2024-10-30","cited_by_count":3,"area":null},{"id":"2502.12088","title":"Meta-Statistical Learning: Supervised Learning of Statistical Estimators","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2111.13185","title":"Learning Conditional Invariance through Cycle Consistency","created":"2021-11-25","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":"2309.16109","title":"Feature Normalization Prevents Collapse of Non-contrastive Learning Dynamics","created":"2023-09-28","cited_by_count":2,"area":null},{"id":"2401.00873","title":"Unifying Self-Supervised Clustering and Energy-Based Models","created":"2023-12-30","cited_by_count":2,"area":null},{"id":"2401.12824","title":"MAPPING: Debiasing Graph Neural Networks for Fair Node Classification with Limited Sensitive Information Leakage","created":"2024-01-23","cited_by_count":2,"area":null},{"id":"2402.06919","title":"TREET: TRansfer Entropy Estimation via Transformers","created":"2024-02-10","cited_by_count":2,"area":null},{"id":"2406.16834","title":"Statistical Error Bounds for GANs with Nonlinear Objective Functionals","created":"2024-06-24","cited_by_count":2,"area":null},{"id":"2409.06890","title":"Learning Representations for Independence Testing","created":"2024-09-10","cited_by_count":2,"area":null},{"id":"2410.01516","title":"Bounds on Lp errors in density ratio estimation via f-divergence loss functions","created":"2024-10-02","cited_by_count":2,"area":null},{"id":"2502.08004","title":"Optimizing Likelihoods via Mutual Information: Bridging Simulation-Based Inference and Bayesian Optimal Experimental Design","created":"2025-02-11","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":"2506.22789","title":"WavShape: Information-Theoretic Speech Representation Learning for Fair and Privacy-Aware Audio Processing","created":"2025-06-28","cited_by_count":2,"area":null},{"id":"2510.25983","title":"Contrastive Predictive Coding Done Right for Mutual Information Estimation","created":"2025-10-29","cited_by_count":2,"area":null},{"id":"2107.03084","title":"Discriminative Mutual Information Estimators for Channel Capacity Learning","created":"2021-07-07","cited_by_count":1,"area":null},{"id":"2111.02042","title":"Recent Advancements in Self-Supervised Paradigms for Visual Feature Representation","created":"2021-11-03","cited_by_count":1,"area":null},{"id":"2202.00129","title":"Fundamental Limits for Sensor-Based Robot Control","created":"2022-01-31","cited_by_count":1,"area":null},{"id":"2210.04209","title":"Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning","created":"2022-10-09","cited_by_count":1,"area":null},{"id":"2211.07533","title":"Generalized Balancing Weights via Deep Neural Networks","created":"2022-11-14","cited_by_count":1,"area":null},{"id":"2310.04557","title":"Measuring Information in Text Explanations","created":"2023-10-06","cited_by_count":1,"area":null},{"id":"2310.13990","title":"A Novel Information-Theoretic Objective to Disentangle Representations for Fair Classification","created":"2023-10-21","cited_by_count":1,"area":null},{"id":"2402.02041","title":"Alpha-divergence loss function for neural density ratio estimation","created":"2024-02-03","cited_by_count":1,"area":null},{"id":"2409.11119","title":"Multi-Cohort Framework with Cohort-Aware Attention and Adversarial Mutual-Information Minimization for Whole Slide Image Classification","created":"2024-09-17","cited_by_count":1,"area":null}],"next_cursor":"100"}