Подписаться
El Houcine Bergou
El Houcine Bergou
UM6P
Подтвержден адрес электронной почты в домене um6p.ma
Название
Процитировано
Процитировано
Год
On the discrepancy between the theoretical analysis and practical implementations of compressed communication for distributed deep learning
A Dutta, EH Bergou, AM Abdelmoniem, CY Ho, AN Sahu, M Canini, ...
Proceedings of the AAAI Conference on Artificial Intelligence 34 (04), 3817-3824, 2020
882020
Grace: A compressed communication framework for distributed machine learning
H Xu, CY Ho, AM Abdelmoniem, A Dutta, EH Bergou, K Karatsenidis, ...
2021 IEEE 41st international conference on distributed computing systems …, 2021
772021
Compressed communication for distributed deep learning: Survey and quantitative evaluation
H Xu, CY Ho, AM Abdelmoniem, A Dutta, EH Bergou, K Karatsenidis, ...
712020
Convergence and complexity analysis of a Levenberg–Marquardt algorithm for inverse problems
EH Bergou, Y Diouane, V Kungurtsev
Journal of Optimization Theory and Applications 185, 927-944, 2020
582020
Stochastic three points method for unconstrained smooth minimization
EH Bergou, E Gorbunov, P Richtárik
SIAM Journal on Optimization 30 (4), 2726-2749, 2020
492020
Levenberg--Marquardt methods based on probabilistic gradient models and inexact subproblem solution, with application to data assimilation
E Bergou, S Gratton, LN Vicente
SIAM/ASA Journal on Uncertainty Quantification 4 (1), 924-951, 2016
382016
Stochastic sign descent methods: New algorithms and better theory
M Safaryan, P Richtárik
International Conference on Machine Learning, 9224-9234, 2021
342021
A subsampling line-search method with second-order results
EH Bergou, Y Diouane, V Kunc, V Kungurtsev, CW Royer
INFORMS Journal on Optimization 4 (4), 403-425, 2022
272022
Hybrid Levenberg–Marquardt and weak-constraint ensemble Kalman smoother method
J Mandel, E Bergou, S Gürol, S Gratton, I Kasanický
Nonlinear Processes in Geophysics 23 (2), 59-73, 2016
272016
On the use of the energy norm in trust-region and adaptive cubic regularization subproblems
E Bergou, Y Diouane, S Gratton
Computational Optimization and Applications 68, 533-554, 2017
252017
A stochastic derivative free optimization method with momentum
E Gorbunov, A Bibi, O Sener, EH Bergou, P Richtárik
arXiv preprint arXiv:1905.13278, 2019
232019
A Stochastic Levenberg--Marquardt Method Using Random Models with Complexity Results
EH Bergou, Y Diouane, V Kungurtsev, CW Royer
SIAM/ASA Journal on Uncertainty Quantification 10 (1), 507-536, 2022
18*2022
On the convergence of a non-linear ensemble Kalman smoother
EH Bergou, S Gratton, J Mandel
Applied Numerical Mathematics 137, 151-168, 2019
162019
A stochastic derivative-free optimization method with importance sampling: Theory and learning to control
A Bibi, EH Bergou, O Sener, B Ghanem, P Richtarik
Proceedings of the AAAI Conference on Artificial Intelligence 34 (04), 3275-3282, 2020
122020
A line-search algorithm inspired by the adaptive cubic regularization framework and complexity analysis
EH Bergou, Y Diouane, S Gratton
Journal of Optimization Theory and Applications 178, 885-913, 2018
122018
The exact condition number of the truncated singular value solution of a linear ill-posed problem
EH Bergou, S Gratton, J Tshimanga
SIAM Journal on Matrix Analysis and Applications 35 (3), 1073-1085, 2014
112014
4DVAR by ensemble Kalman smoother
J Mandel, E Bergou, S Gratton
arXiv preprint arXiv:1304.5271, 2013
92013
Client selection in federated learning based on gradients importance
O Marnissi, HE Hammouti, EH Bergou
AIP Conference Proceedings 3034 (1), 2024
42024
Personalized federated learning with communication compression
EH Bergou, K Burlachenko, A Dutta, P Richtárik
arXiv preprint arXiv:2209.05148, 2022
42022
Convergence and Iteration Complexity Analysis of a Levenberg–Marquardt Algorithm for Zero and Non-zero Residual Inverse Problems
E Bergou, Y Diouane, V Kungurtsev
Paper, 2018
42018
В данный момент система не может выполнить эту операцию. Повторите попытку позднее.
Статьи 1–20