Chaining Meets Chain Rule: Multilevel Entropic Regularization and Training of Neural Nets

26 June 2019

Papers citing "Chaining Meets Chain Rule: Multilevel Entropic Regularization and Training of Neural Nets"

6 / 6 papers shown

Title
Information-Theoretic Analysis of Minimax Excess Risk Hassan Hafez-Kolahi Behrad Moniri S. Kasaei 17 4 0 15 Feb 2022
On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and Implications Ziqiao Wang Yongyi Mao FedML MLT 37 22 0 07 Oct 2021
Characterizing the Generalization Error of Gibbs Algorithm with Symmetrized KL information Gholamali Aminian Yuheng Bu Laura Toni M. Rodrigues G. Wornell 24 4 0 28 Jul 2021
Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms Mahdi Haghifam Jeffrey Negrea Ashish Khisti Daniel M. Roy Gintare Karolina Dziugaite 29 105 0 27 Apr 2020
Representing smooth functions as compositions of near-identity functions with implications for deep network optimization Peter L. Bartlett S. Evans Philip M. Long 71 31 0 13 Apr 2018
Pac-Bayesian Supervised Classification: The Thermodynamics of Statistical Learning O. Catoni 148 454 0 03 Dec 2007