Information Theory

Temperature-scaling surprisal estimates improve fit to human reading times – but does it do so for the “right reasons”? ACL 2024 Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussians ICML 2024 The Sample Complexity of Simple Binary Hypothesis Testing COLT 2024 Thresholds for Reconstruction of Random Hypergraphs From Graph Projections COLT 2024 Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning NeurIPS 2024 Towards a Similarity-adjusted Surprisal Theory EMNLP 2024 Universal Exact Compression of Differentially Private Mechanisms NeurIPS 2024 VOLIMET: A Parallel Corpus of Literal and Metaphorical Verb-Object Pairs for English–German and English–French NAACL 2024 Which Information Matters? Dissecting Human-written Multi-document Summaries with Partial Information Decomposition ACL 2024 A linear time approximation of Wasserstein distance with word embedding selection EMNLP 2023 A Mutual Information-based Approach to Quantifying Logography in Japanese and Sumerian ACL 2023 Analyzing Privacy Leakage in Machine Learning via Multiple Hypothesis Testing: A Lesson From Fano ICML 2023 An Information-Theoretic Analysis of Nonstationary Bandit Learning ICML 2023 An Information-Theoretic Evaluation of Generative Models in Learning Multi-modal Distributions NeurIPS 2023 An Information Theory Perspective on Variance-Invariance-Covariance Regularization NeurIPS 2023 A Rigorous Information-Theoretic Definition of Redundancy and Relevancy in Feature Selection Based on (Partial) Information Decomposition JMLR 2023 A unified framework for information-theoretic generalization bounds NeurIPS 2023 Causal information splitting: Engineering proxy features for robustness to distribution shifts UAI 2023 Compressing Tabular Data via Latent Variable Estimation ICML 2023 Controlling Wasserstein Distances by Kernel Norms with Application to Compressive Statistical Learning JMLR 2023 Deep Graph Structural Infomax AAAI 2023 DIET: Conditional independence testing with marginal dependence measures of residual information AISTATS 2023 Entropic characterization of optimal rates for learning Gaussian mixtures COLT 2023 Estimating the Rate-Distortion Function by Wasserstein Gradient Descent NeurIPS 2023 Estimating Total Correlation with Mutual Information Estimators AISTATS 2023