Følg
Scott Pesme
Scott Pesme
PhD at EPFL
Verificeret mail på epfl.ch - Startside
Titel
Citeret af
Citeret af
År
Implicit bias of sgd for diagonal linear networks: a provable benefit of stochasticity
S Pesme, L Pillaud-Vivien, N Flammarion
Neurips 2021, 2021
852021
Online robust regression via sgd on the l1 loss
S Pesme, N Flammarion
Neurips 2020, 2020
372020
(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
25*2023
Saddle-to-Saddle Dynamics in Diagonal Linear Networks
S Pesme, N Flammarion
Neurips 2023, 2023
202023
On convergence-diagnostic based step sizes for stochastic gradient descent
S Pesme, A Dieuleveut, N Flammarion
ICML 2020, 2020
202020
Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks
HG Papazov, S Pesme, N Flammarion
AISTATS 2024, 2024
2024
Systemet kan ikke foretage handlingen nu. Prøv igen senere.
Artikler 1–6