‪Scott Pesme‬ - ‪Google Scholar‬

Get my own profile

Cited by

	All	Since 2019
Citations	184	184
h-index	5	5
i10-index	5	5

0

90

45

2019202020212022202320241 14 37 86 46

Co-authors

Nicolas FlammarionEPFLVerified email at epfl.ch
Loucas Pillaud-VivienCourant Institute of Mathematics, NYU / Flatiron Institute, New YorkVerified email at flatironinstitute.org
Mathieu EvenEcole Normale Supérieure, InriaVerified email at ens.fr
Suriya GunasekarMSR RedmondVerified email at ttic.edu
Aymeric DieuleveutProfessor, Ecole Polytechnique, FranceVerified email at polytechnique.edu

Scott Pesme

Scott Pesme

PhD at EPFL

Verified email at epfl.ch - Homepage

Machine Learning Optimisation


Title Sort by citations Sort by year Sort by title	Cited by Cited by	Year
Implicit bias of sgd for diagonal linear networks: a provable benefit of stochasticity S Pesme, L Pillaud-Vivien, N Flammarion Neurips 2021, 2021	85	2021
Online robust regression via sgd on the l1 loss S Pesme, N Flammarion Neurips 2020, 2020	35	2020
(S) GD over Diagonal Linear Networks: Implicit Regularisation, Large Stepsizes and Edge of Stability M Even, S Pesme, S Gunasekar, N Flammarion Neurips 2023, 2023	24*	2023
Saddle-to-Saddle Dynamics in Diagonal Linear Networks S Pesme, N Flammarion Neurips 2023, 2023	20	2023
On convergence-diagnostic based step sizes for stochastic gradient descent S Pesme, A Dieuleveut, N Flammarion ICML 2020, 2020	20	2020
Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks HG Papazov, S Pesme, N Flammarion AISTATS 2024, 2024		2024

The system can't perform the operation now. Try again later.

Articles 1–6