Unpacking Information Bottlenecks: Unifying Information-Theoretic Objectives in Deep Learning

27 March 2020

Papers citing "Unpacking Information Bottlenecks: Unifying Information-Theoretic Objectives in Deep Learning"

14 / 14 papers shown

Title
Towards Understanding Variants of Invariant Risk Minimization through the Lens of Calibration Kotaro Yoshida Hiroki Naganuma 68 1 0 31 Jan 2024
Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression I. Butakov Alexander Tolmachev S. Malanchuk A. Neopryatnaya Alexey Frolov K. Andreev 16 4 0 13 May 2023
Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utility Behrooz Razeghi Flavio du Pin Calmon Deniz Gunduz S. Voloshynovskiy 27 15 0 11 Jul 2022
Compressing Features for Learning with Noisy Labels Yingyi Chen S. Hu Xin Shen C. Ai Johan A. K. Suykens NoLa 13 13 0 27 Jun 2022
Optimal Randomized Approximations for Matrix based Renyi's Entropy Yuxin Dong Tieliang Gong Shujian Yu Chen Li 24 7 0 16 May 2022
A Note on "Assessing Generalization of SGD via Disagreement" Andreas Kirsch Y. Gal FedML UQCV 21 15 0 03 Feb 2022
Conditional entropy minimization principle for learning domain invariant representation features Thuan Q. Nguyen Boyang Lyu Prakash Ishwar matthias. scheutz Shuchin Aeron OOD 27 7 0 25 Jan 2022
A Closer Look at the Adversarial Robustness of Information Bottleneck Models I. Korshunova David Stutz Alexander A. Alemi Olivia Wiles Sven Gowal 19 3 0 12 Jul 2021
A Practical & Unified Notation for Information-Theoretic Quantities in ML Andreas Kirsch Y. Gal 25 7 0 22 Jun 2021
Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization Kartik Ahuja Ethan Caballero Dinghuai Zhang Jean-Christophe Gagnon-Audet Yoshua Bengio Ioannis Mitliagkas Irina Rish OOD 15 248 0 11 Jun 2021
Deep Deterministic Uncertainty: A Simple Baseline Jishnu Mukhoti Andreas Kirsch Joost R. van Amersfoort Philip H. S. Torr Y. Gal UD UQCV PER BDL 18 145 0 23 Feb 2021
DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation Alexandre Ramé Matthieu Cord FedML 42 51 0 14 Jan 2021
Action and Perception as Divergence Minimization Danijar Hafner Pedro A. Ortega Jimmy Ba Thomas Parr Karl J. Friston N. Heess 13 51 0 03 Sep 2020
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning Y. Gal Zoubin Ghahramani UQCV BDL 285 9,136 0 06 Jun 2015