v1v2 (latest)

A Study of Condition Numbers for First-Order Optimization

International Conference on Artificial Intelligence and Statistics (AISTATS), 2020

10 December 2020

Charles Guille-Escuret

Baptiste Goujaud

M. Girotti

Alexia Jolicoeur-Martineau

ArXiv (abs)PDF HTML

Papers citing "A Study of Condition Numbers for First-Order Optimization"

6 / 6 papers shown

Model Immunization from a Condition Number Perspective

183

29 May 2025

New Perspectives on the Polyak Stepsize: Surrogate Functions and Negative Results

Francesco Orabona

Ryan DÓrazio

425

26 May 2025

Understanding Adam Requires Better Rotation Dependent Assumptions

Tianyue H. Zhang

Lucas Maes

Alexia Jolicoeur-Martineau

Damien Scieur

Simon Lacoste-Julien

Charles Guille-Escuret

345

25 Oct 2024

No Wrong Turns: The Simple Geometry Of Neural Networks Optimization PathsInternational Conference on Machine Learning (ICML), 2023

Charles Guille-Escuret

Hiroki Naganuma

Kilian Fatras

Ioannis Mitliagkas

231

20 Jun 2023

$On the Convergence of AdaGrad(Norm) on $\R^{d}$: Beyond Convexity, Non-Asymptotic Rate and Acceleration$

On the Convergence of AdaGrad(Norm) on

\R^{d}

: Beyond Convexity, Non-Asymptotic Rate and Acceleration

437

29 Sep 2022

Activated Gradients for Deep Neural NetworksIEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2021

201

213

09 Jul 2021