Phenomenology of Double Descent in Finite-Width Neural Networks

14 March 2022

Papers citing "Phenomenology of Double Descent in Finite-Width Neural Networks"

4 / 4 papers shown

Title
Theoretical characterisation of the Gauss-Newton conditioning in Neural Networks Jim Zhao Sidak Pal Singh Aurelien Lucchi AI4CE 43 0 0 04 Nov 2024
Unraveling the Hessian: A Key to Smooth Convergence in Loss Function Landscapes Nikita Kiselev Andrey Grabovoy 51 1 0 18 Sep 2024
Two Facets of SDE Under an Information-Theoretic Lens: Generalization of SGD via Training Trajectories and via Terminal States Ziqiao Wang Yongyi Mao 27 10 0 19 Nov 2022
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 281 2,889 0 15 Sep 2016