← Optimization & Theory
Machine Learning › Optimization & Theory ›

Information Theory

313 directly classified papers

Papers per year

Papers

A Reparametrization-Invariant Sharpness Measure Based on Information Geometry NIPS 2022
Evaluated CMI Bounds for Meta Learning: Tightness and Expressiveness NIPS 2022
Tight Mutual Information Estimation With Contrastive Fenchel-Legendre Optimization NIPS 2022
On Leave-One-Out Conditional Mutual Information For Generalization NIPS 2022
Domain Generalization without Excess Empirical Risk NIPS 2022
$k$-Sliced Mutual Information: A Quantitative Study of Scalability with Dimension NIPS 2022
Regret Bounds for Information-Directed Reinforcement Learning NIPS 2022
Information-Theoretic Characterization of the Generalization Error for Iterative Semi-Supervised Learning JMLR 2022
What Has Been Enhanced in my Knowledge-Enhanced Language Model? EMNLP 2022
Adaptive Data Analysis with Correlated Observations ICML 2022
ITSA: An Information-Theoretic Approach to Automatic Shortcut Avoidance and Domain Generalization in Stereo Matching Networks CVPR 2022
Sequential and Parallel Constrained Max-value Entropy Search via Information Lower Bound ICML 2022
Quantification and Analysis of Layer-wise and Pixel-wise Information Discarding ICML 2022
Information bottleneck theory of high-dimensional regression: relevancy, efficiency and optimality NIPS 2022
A Functional Information Perspective on Model Interpretation ICML 2022
An Information-theoretic Approach to Distribution Shifts NIPS 2021
Partition and Code: learning how to compress graphs NIPS 2021
Measuring Dependence with Matrix-based Entropy Functional AAAI 2021
Whitening and Second Order Optimization Both Make Information in the Dataset Unusable During Training, and Can Reduce or Prevent Generalization ICML 2021
Tighter Expected Generalization Error Bounds via Wasserstein Distance NIPS 2021
Learning Smooth and Fair Representations AISTATS 2021
Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning ICML 2021
A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations IJCNLP 2021
Deciding What to Learn: A Rate-Distortion Approach ICML 2021
SMURF: SeMantic and linguistic UndeRstanding Fusion for Caption Evaluation via Typicality Analysis IJCNLP 2021