SANE: The phases of gradient descent through Sharpness Adjusted Number of Effective parameters

29 May 2023

Papers citing "SANE: The phases of gradient descent through Sharpness Adjusted Number of Effective parameters"

10 / 10 papers shown

Title
Visualizing high-dimensional loss landscapes with Hessian directions Lucas Böttcher Gregory R. Wheeler 66 14 0 28 Aug 2022
Analyzing Sharpness along GD Trajectory: Progressive Sharpening and Edge of Stability Z. Li Zixuan Wang Jian Li 53 47 0 26 Jul 2022
Sharpness-Aware Minimization for Efficiently Improving Generalization Pierre Foret Ariel Kleiner H. Mobahi Behnam Neyshabur AAML 192 1,350 0 03 Oct 2020
Rethinking Parameter Counting in Deep Models: Effective Dimensionality Revisited Wesley J. Maddox Gregory W. Benton A. Wilson 116 61 0 04 Mar 2020
Deep Ensembles: A Loss Landscape Perspective Stanislav Fort Huiyi Hu Balaji Lakshminarayanan OOD UQCV 121 628 0 05 Dec 2019
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms Han Xiao Kashif Rasul Roland Vollgraf 283 8,904 0 25 Aug 2017
Early Stopping without a Validation Set Maren Mahsereci Lukas Balles Christoph Lassner Philipp Hennig 65 88 0 28 Mar 2017
Eigenvalues of the Hessian in Deep Learning: Singularity and Beyond Levent Sagun Léon Bottou Yann LeCun UQCV 91 236 0 22 Nov 2016
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 427 2,941 0 15 Sep 2016
Cyclical Learning Rates for Training Neural Networks L. Smith ODL 210 2,529 0 03 Jun 2015