Information Theory

Prediction-Oriented Bayesian Active Learning AISTATS 2023 Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework NeurIPS 2023 Recovery Bounds on Class-Based Optimal Transport: A Sum-of-Norms Regularization Framework ICML 2023 Revisiting Entropy Rate Constancy in Text EMNLP 2023 Robust and Fast Measure of Information via Low-Rank Representation AAAI 2023 Simple Binary Hypothesis Testing under Local Differential Privacy and Communication Constraints COLT 2023 Statistical and Computational Limits for Tensor-on-Tensor Association Detection COLT 2023 Syntax and Geometry of Information ACL 2023 The Sample Complexity of Approximate Rejection Sampling With Applications to Smoothed Online Learning COLT 2023 The s-value: evaluating stability with respect to distributional shifts NeurIPS 2023 Tighter Information-Theoretic Generalization Bounds from Supersamples ICML 2023 Tokenization and the Noiseless Channel ACL 2023 Understanding the Generalization Ability of Deep Learning Algorithms: A Kernelized Rényi's Entropy Perspective IJCAI 2023 Unified Lower Bounds for Interactive High-dimensional Estimation under Information Constraints NeurIPS 2023 Unified Perspective on Probability Divergence via the Density-Ratio Likelihood: Bridging KL-Divergence and Integral Probability Metrics AISTATS 2023 “World Knowledge” in Multiple Choice Reading Comprehension EACL 2023 k-Sliced Mutual Information: A Quantitative Study of Scalability with Dimension NeurIPS 2022 A Functional Information Perspective on Model Interpretation ICML 2022 Algorithms for the Communication of Samples ICML 2022 Analyzing Wrap-Up Effects through an Information-Theoretic Lens ACL 2022 A time-resolved theory of information encoding in recurrent neural networks NeurIPS 2022 Batch Greenkhorn Algorithm for Entropic-Regularized Multimarginal Optimal Transport: Linear Rate of Convergence and Iteration Complexity ICML 2022 Beyond Images: Label Noise Transition Matrix Estimation for Tasks with Lower-Quality Features ICML 2022 C2DN: How to Harness Erasure Codes at the Edge for Efficient Content Delivery NSDI 2022 Characterizing and Understanding the Generalization Error of Transfer Learning with Gibbs Algorithm AISTATS 2022