Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent

23 May 2022

Papers citing "Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent"

6 / 6 papers shown

Title
Generalization Guarantees for Multi-View Representation Learning and Application to Regularization via Gaussian Product Mixture Prior Milad Sefidgaran Abdellatif Zaidi Piotr Krasnowski 44 0 0 25 Apr 2025
Generalization Guarantees for Representation Learning via Data-Dependent Gaussian Mixture Priors Milad Sefidgaran A. Zaidi Piotr Krasnowski 80 1 0 21 Feb 2025
Privacy of SGD under Gaussian or Heavy-Tailed Noise: Guarantees without Gradient Clipping Umut Simsekli Mert Gurbuzbalaban S. Yıldırım Lingjiong Zhu 30 2 0 04 Mar 2024
Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions Anant Raj Lingjiong Zhu Mert Gurbuzbalaban Umut Simsekli 21 15 0 27 Jan 2023
Stochastic Training is Not Necessary for Generalization Jonas Geiping Micah Goldblum Phillip E. Pope Michael Moeller Tom Goldstein 81 72 0 29 Sep 2021
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima N. Keskar Dheevatsa Mudigere J. Nocedal M. Smelyanskiy P. T. P. Tang ODL 273 2,878 0 15 Sep 2016