Aymeric Dieuleveut
Aymeric Dieuleveut
Assistant Professor, Ecole Polytechnique, France
Verified email at polytechnique.edu - Homepage
Title
Cited by
Cited by
Year
Nonparametric stochastic approximation with large step-sizes
A Dieuleveut, F Bach
The Annals of Statistics 44 (4), 1363-1399, 2016
1292016
Harder, better, faster, stronger convergence rates for least-squares regression
A Dieuleveut, N Flammarion, F Bach
The Journal of Machine Learning Research 18 (1), 3520-3570, 2017
1042017
Bridging the gap between constant step size stochastic gradient descent and markov chains
A Dieuleveut, A Durmus, F Bach
Annals of Statistics 48 (Number 3 (2020)), 1348-1382., 2020
962020
Unsupervised scalable representation learning for multivariate time series
JY Franceschi, A Dieuleveut, M Jaggi
33rd Conference on Neural Information Processing Systems (NeurIPS 2019), 2019
642019
Context mover’s distance & barycenters: Optimal transport of contexts for building representations
SP Singh, A Hug, A Dieuleveut, M Jaggi
International Conference on Artificial Intelligence and Statistics, 3437-3449, 2020
23*2020
Communication trade-offs for Local-SGD with large step size
A Dieuleveut, KK Patel
Advances in Neural Information Processing Systems 32, 13601-13612, 2019
142019
Communication trade-offs for synchronized distributed SGD with large step size
KK Patel, A Dieuleveut
arXiv preprint arXiv:1904.11325, 2019
102019
Artemis: tight convergence guarantees for bidirectional compression in federated learning
C Philippenko, A Dieuleveut
arXiv e-prints, arXiv: 2006.14591, 2020
9*2020
On convergence-diagnostic based step sizes for stochastic gradient descent
S Pesme, A Dieuleveut, N Flammarion
International Conference on Machine Learning, 7641-7651, 2020
42020
Debiasing Averaged Stochastic Gradient Descent to handle missing values
A Sportisse, C Boyer, A Dieuleveut, J Josses
Advances in Neural Information Processing Systems 33, 2020
3*2020
QLSD: Quantised Langevin stochastic dynamics for Bayesian federated learning
M Vono, V Plassier, A Durmus, A Dieuleveut, E Moulines
arXiv preprint arXiv:2106.00797, 2021
12021
Preserved central model for faster bidirectional compression in distributed settings
C Philippenko, A Dieuleveut
arXiv preprint arXiv:2102.12528, 2021
12021
Stochastic approximation in Hilbert spaces
A Dieuleveut
Paris Sciences et Lettres (ComUE), 2017
12017
Federated Expectation Maximization with heterogeneity mitigation and variance reduction
A Dieuleveut, G Fort, E Moulines, G Robin
2021
Super-Acceleration with Cyclical Step-sizes
B Goujaud, D Scieur, A Dieuleveut, A Taylor, F Pedregosa
arXiv preprint arXiv:2106.09687, 2021
2021
Communication trade-offs for synchronized distributed SGD with large step size
A DIEULEVEUT
2017
Wasserstein is all you need Download PDF
SP Singh, A Hug, A Dieuleveut, M Jaggi
On Convergence-Diagnostic based Step Sizes for Stochastic Gradient Descent
A Dieuleveut
Sciper ID 290153 Affiliated labs MLO
A Dieuleveut
Learning for Multivariate Time Series
JY Franceschi, A Dieuleveut, M Jaggi
The system can't perform the operation now. Try again later.
Articles 1–20