Suivre
Sholom Schechtman
Sholom Schechtman
Télécom SudParis
Adresse e-mail validée de telecom-sudparis.eu
Titre
Citée par
Citée par
Année
Convergence of constant step stochastic gradient descent for non-smooth non-convex functions
P Bianchi, W Hachem, S Schechtman
Set-Valued and Variational Analysis, 2022
482022
Stochastic optimization with momentum: convergence, fluctuations, and traps avoidance
A Barakat, P Bianchi, W Hachem, S Schechtman
Electronic Journal of Statistics 15 (2), 3892-3947, 2020
152020
Stochastic Subgradient Descent Escapes Active Strict Saddles on Weakly Convex Functions
P Bianchi, W Hachem, S Schechtman
Mathematics of Operations Research, 2023
122023
Passty Langevin
P Bianchi, A Salim, S Schechtman
Conference on Machine Learning (CAp), 2019
52019
Orthogonal Directions Constrained Gradient Method: from non-linear equality constraints to Stiefel manifold
S Schechtman, D Tiapkin, M Muehlebach, E Moulines
Conference on Learning Theory, 1228--1258, 2023
42023
AskewSGD: an annealed interval-constrained optimisation method to train quantized neural networks
L Leconte, S Schechtman, E Moulines
International Conference on Artificial Intelligence and Statistics, 3644-3663, 2023
32023
Stochastic proximal subgradient descent oscillates in the vicinity of its accumulation set
S Schechtman
Optimization Letters, 2022
32022
First-order constrained optimization: Non-smooth dynamical system viewpoint
S Schechtman, D Tiapkin, E Moulines, MI Jordan, M Muehlebach
IFAC-PapersOnLine 55 (16), 236-241, 2022
32022
SignSVRG: fixing SignSGD via variance reduction
E Chzhen, S Schechtman
arXiv preprint arXiv:2305.13187, 2023
12023
The gradient's limit of a definable family of functions is a conservative set-valued field
S Schechtman
arXiv preprint arXiv:2402.08272, 2024
2024
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–10