Small steps and giant leaps: Minimal Newton solvers for Deep Learning

Small steps and giant leaps: Minimal Newton solvers for Deep Learning

21 May 2018

João F. Henriques

Sébastien Ehrhardt

Andrea Vedaldi

ArXiv (abs)PDF HTML

Papers citing "Small steps and giant leaps: Minimal Newton solvers for Deep Learning"

8 / 8 papers shown

Title
Statistical and Computational Guarantees for Influence Diagnostics Jillian R. Fisher Lang Liu Krishna Pillutla Y. Choi Zaïd Harchaoui TDI 54 0 0 08 Dec 2022
A Stochastic Bundle Method for Interpolating Networks Alasdair Paren Leonard Berrada Rudra P. K. Poudel M. P. Kumar 64 4 0 29 Jan 2022
KOALA: A Kalman Optimization Algorithm with Loss Adaptivity A. Davtyan Sepehr Sameni L. Cerkezi Givi Meishvili Adam Bielski Paolo Favaro ODL 158 3 0 07 Jul 2021
Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers Robin M. Schmidt Frank Schneider Philipp Hennig ODL 202 168 0 03 Jul 2020
Sketchy Empirical Natural Gradient Methods for Deep Learning Minghan Yang Dong Xu Zaiwen Wen Mengyun Chen Pengxiang Xu 27 13 0 10 Jun 2020
Deep Neural Network Learning with Second-Order Optimizers -- a Practical Study with a Stochastic Quasi-Gauss-Newton Method C. Thiele Mauricio Araya-Polo D. Hohl ODL 21 2 0 06 Apr 2020
Training Neural Networks for and by Interpolation Leonard Berrada Andrew Zisserman M. P. Kumar 3DH 74 63 0 13 Jun 2019
An Adaptive Remote Stochastic Gradient Method for Training Neural Networks Yushu Chen Hao Jing Wenlai Zhao Zhiqiang Liu Haohuan Fu Lián Qiao Wei Xue Guangwen Yang ODL 49 2 0 04 May 2019