The asymptotic spectrum of the Hessian of DNN throughout training

1 October 2019

Papers citing "The asymptotic spectrum of the Hessian of DNN throughout training"

10 / 10 papers shown

Title
Theoretical characterisation of the Gauss-Newton conditioning in Neural Networks Jim Zhao Sidak Pal Singh Aurelien Lucchi AI4CE 48 0 0 04 Nov 2024
Spectral alignment of stochastic gradient descent for high-dimensional classification tasks Gerard Ben Arous Reza Gheissari Jiaoyang Huang Aukosh Jagannath 35 13 0 04 Oct 2023
Bottleneck Structure in Learned Features: Low-Dimension vs Regularity Tradeoff Arthur Jacot MLT 28 13 0 30 May 2023
On the Overlooked Structure of Stochastic Gradients Zeke Xie Qian-Yuan Tang Mingming Sun P. Li 33 6 0 05 Dec 2022
Second-order regression models exhibit progressive sharpening to the edge of stability Atish Agarwala Fabian Pedregosa Jeffrey Pennington 44 26 0 10 Oct 2022
Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning Haoxiang Wang Yite Wang Ruoyu Sun Bo-wen Li 35 27 0 17 Mar 2022
On the Power-Law Hessian Spectrums in Deep Learning Zeke Xie Qian-Yuan Tang Yunfeng Cai Mingming Sun P. Li ODL 42 9 0 31 Jan 2022
Fed-ensemble: Improving Generalization through Model Ensembling in Federated Learning Naichen Shi Fan Lai Raed Al Kontar Mosharaf Chowdhury FedML 36 36 0 21 Jul 2021
Spectra of the Conjugate Kernel and Neural Tangent Kernel for linear-width neural networks Z. Fan Zhichao Wang 44 71 0 25 May 2020
The Loss Surfaces of Multilayer Networks A. Choromańska Mikael Henaff Michaël Mathieu Gerard Ben Arous Yann LeCun ODL 186 1,186 0 30 Nov 2014