HesScale: Scalable Computation of Hessian Diagonals

20 October 2022

Papers citing "HesScale: Scalable Computation of Hessian Diagonals"

6 / 6 papers shown

Title
Connecting Parameter Magnitudes and Hessian Eigenspaces at Scale using Sketched Methods Andres Fernandez Frank Schneider Maren Mahsereci Philipp Hennig 33 0 0 20 Apr 2025
Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement Zhehao Huang Xinwen Cheng JingHao Zheng Haoran Wang Zhengbao He Tao Li X. Huang MU 47 5 0 29 Sep 2024
Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning Mohamed Elsayed A. R. Mahmood CLL 50 20 0 31 Mar 2024
Tradeoffs of Diagonal Fisher Information Matrix Estimators Alexander Soen Ke Sun 21 1 0 08 Feb 2024
Directions of Curvature as an Explanation for Loss of Plasticity Alex Lewandowski Haruto Tanaka Dale Schuurmans Marlos C. Machado 19 5 0 30 Nov 2023
Utility-based Perturbed Gradient Descent: An Optimizer for Continual Learning Mohamed Elsayed A. R. Mahmood CLL 21 6 0 07 Feb 2023