Aymeric Dieuleveut

33
Documents

Publications

Publications

PEPit: computer-assisted worst-case analyses of first-order optimization methods in Python

Baptiste Goujaud , Céline Moucer , François Glineur , Julien Hendrickx , Adrien Taylor et al.
Mathematical Programming Computation, 2024, 16 (3), pp.337-367. ⟨10.1007/s12532-024-00259-7⟩
Article dans une revue hal-03780353 v1
Image document

Stochastic Approximation Beyond Gradient for Signal Processing and Machine Learning

Aymeric Dieuleveut , Gersende Fort , Eric Moulines , Hoi-To Wai
IEEE Transactions on Signal Processing, 2023, 71, pp.3117-3148. ⟨10.1109/TSP.2023.3301121⟩
Article dans une revue hal-03979922 v1

Counter-Examples in First-Order Optimization: A Constructive Approach

Baptiste Goujaud , Aymeric Dieuleveut , Adrien Taylor
IEEE Control Systems Letters, 2023, 7, pp.2485-2490. ⟨10.1109/LCSYS.2023.3286277⟩
Article dans une revue hal-04384238 v1
Image document

Bridging the Gap between Constant Step Size Stochastic Gradient Descent and Markov Chains

Aymeric Dieuleveut , Alain Durmus , Francis Bach
Annals of Statistics, 2020, 48 (3), ⟨10.1214/19-AOS1850⟩
Article dans une revue hal-01565514 v2
Image document

Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression

Aymeric Dieuleveut , Nicolas Flammarion , Francis Bach
Journal of Machine Learning Research, 2017, 17 (101), pp.1-51
Article dans une revue hal-01275431 v2
Image document

Non-parametric Stochastic Approximation with Large Step sizes

Aymeric Dieuleveut , Francis Bach
Annals of Statistics, 2015, 44 (4), ⟨10.1214/15-AOS1391⟩
Article dans une revue hal-01053831 v2
Image document

Proving Linear Mode Connectivity of Neural Networks via Optimal Transport

Damien Ferbach , Baptiste Goujaud , Gauthier Gidel , Aymeric Dieuleveut
27th International Conference on Artificial Intelligence and Statistics (AISTATS 2024), May 2024, Valence, Spain. pp.3853-3861
Communication dans un congrès hal-04554453 v1
Image document

Naive imputation implicitly regularizes high-dimensional linear models

Alexis Ayme , Claire Boyer , Aymeric Dieuleveut , Erwan Scornet
International Conference on Machine Learning, Jul 2023, Hawai, USA, United States
Communication dans un congrès hal-03958825 v1
Image document

On Fundamental Proof Structures in First-Order Optimization

Baptiste Goujaud , Aymeric Dieuleveut , Adrien Taylor
Conference on Decision and Control, Tutorial sessions, Dec 2023, Marina Bay Sands, Singapore. ⟨10.48550/arXiv.2310.02015⟩
Communication dans un congrès hal-04384178 v1
Image document

Compression with Exact Error Distribution for Federated Learning

Mahmoud Hegazy , Rémi Leluc , Cheuk Ting Li , Aymeric Dieuleveut
International Conference on Artificial Intelligence and Statistics, May 2024, Valencia (Espagne), Spain. pp.613-621
Communication dans un congrès hal-04554506 v1
Image document

Conformal Prediction with Missing Values

Margaux Zaffran , Aymeric Dieuleveut , Julie Josse , Yaniv Romano
ICML 2023 - 40 th International Conference on Machine Learning, Jul 2023, Honolulu (Hawai), United States. pp.40578
Communication dans un congrès hal-03896384 v4
Image document

QLSD: Quantised Langevin Stochastic Dynamics for Bayesian Federated Learning

Maxime Vono , Vincent Plassier , Alain Durmus , Aymeric Dieuleveut , Eric Moulines
International Conference on Artificial Intelligence and Statistics, 2022, Online, France
Communication dans un congrès hal-03589952 v1
Image document

Differentially Private Federated Learning on Heterogeneous Data

Maxence Noble , Aurélien Bellet , Aymeric Dieuleveut
Proceedings of The 25th International Conference on Artificial Intelligence and Statistics (AISTATS), 2022, Virtual, Spain
Communication dans un congrès hal-03905078 v1
Image document

Adaptive Conformal Predictions for Time Series

Margaux Zaffran , Olivier Féron , Yannig Goude , Julie Josse , Aymeric Dieuleveut
ICML 2022 - 39th International Conference on Machine Learning, Jul 2022, Baltimore - Maryland, United States
Communication dans un congrès hal-03573934 v2

Super-Acceleration with Cyclical Step-sizes

Baptiste Goujaud , Damien Scieur , Aymeric Dieuleveut , Adrien Taylor , Fabian Pedregosa
International Conference on Artificial Intelligence and Statistics, Mar 2022, Virtual conference, France
Communication dans un congrès hal-03377367 v1

FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings

Jean Ogier Du Terrail , Samy-Safwan Ayed , Edwige Cyffers , Felix Grimberg , Chaoyang He et al.
NeurIPS 2022 - Thirty-sixth Conference on Neural Information Processing Systems, Nov 2022, New Orleans, United States
Communication dans un congrès hal-03900026 v1
Image document

Near-optimal rate of consistency for linear models with missing values

Alexis Ayme , Claire Boyer , Aymeric Dieuleveut , Erwan Scornet
International Conference on Machine Learning,, Jul 2022, Baltimore MD, United States
Communication dans un congrès hal-03552109 v2
Image document

Preserved central model for faster bidirectional compression in distributed settings

Constantin Philippenko , Aymeric Dieuleveut
35th Conference on Neural Information Processing Systems, Dec 2021, Virtual-only Conference, France. pp.2387-2399, ⟨10.48550/arXiv.2102.12528⟩
Communication dans un congrès hal-04255271 v1
Image document

Federated Expectation Maximization with heterogeneity mitigation and variance reduction

Aymeric Dieuleveut , Gersende Fort , Eric Moulines , Geneviève Robin
NeurIPS 2021 - 35th Conference on Neural Information Processing Systems, Dec 2021, Sydney, Australia. ⟨10.48550/arXiv.2111.02083⟩
Communication dans un congrès hal-03333516 v3
Image document

On Convergence-Diagnostic based Step Sizes for Stochastic Gradient Descent

Scott Pesme , Aymeric Dieuleveut , Nicolas Flammarion
37th International Conference on Machine Learning (ICML 2020), Jul 2020, Vienne (en ligne), Austria. pp.119:7641-7651
Communication dans un congrès hal-04554421 v1
Image document

Debiasing Stochastic Gradient Descent to handle missing values

Aude Sportisse , Claire Boyer , Aymeric Dieuleveut , Julie Josse
NeurIPS 2020 - 34th Conference on Neural Information Processing Systems, Dec 2020, Vancouver, Canada
Communication dans un congrès hal-02483651 v2
Image document

Unsupervised Scalable Representation Learning for Multivariate Time Series

Jean-Yves Franceschi , Aymeric Dieuleveut , Martin Jaggi
Thirty-third Conference on Neural Information Processing Systems, Neural Information Processing Systems Foundation, Dec 2019, Vancouver, Canada. pp.4650--4661
Communication dans un congrès hal-01998101 v4
Image document

Unsupervised Scalable Representation Learning for Multivariate Time Series

Jean-Yves Franceschi , Aymeric Dieuleveut , Martin Jaggi
Hanna Wallach; Hugo Larochelle; Alina Beygelzimer; Florence d'Alché-Buc; Emily Fox; Roman Garnett. Thirty-third Conference on Neural Information Processing Systems, Dec 2019, Vancouver, Canada. Curran Associates, Inc., 32, Advances in Neural Information Processing Systems
Poster de conférence hal-02320167 v2
Image document

Refined Analysis of Federated Averaging's Bias and Federated Richardson-Romberg Extrapolation

Paul Mangold , Alain Durmus , Aymeric Dieuleveut , Sergey Samsonov , Eric Moulines
2025
Pré-publication, Document de travail hal-04878343 v1
Image document

Random features models: a way to study the success of naive imputation

Alexis Ayme , Claire Boyer , Aymeric Dieuleveut , Erwan Scornet
2024
Pré-publication, Document de travail hal-04440304 v1
Image document

Sliced-Wasserstein Estimation with Spherical Harmonics as Control Variates

Rémi Leluc , Aymeric Dieuleveut , François Portier , Johan Segers , Aigerim Zhuman
2024
Pré-publication, Document de travail hal-04438124 v1

Provable non-accelerations of the heavy-ball method

Baptiste Goujaud , Adrien Taylor , Aymeric Dieuleveut
2024
Pré-publication, Document de travail hal-04384188 v1
Image document

Compressed and distributed least-squares regression: convergence rates with applications to Federated Learning

Constantin Philippenko , Aymeric Dieuleveut
2023
Pré-publication, Document de travail hal-04350090 v1

Optimal first-order methods for convex functions with a quadratic upper bound

Baptiste Goujaud , Adrien Taylor , Aymeric Dieuleveut
2022
Pré-publication, Document de travail hal-03780321 v1
Image document

Differentially Private Federated Learning on Heterogeneous Data

Maxence Noble , Aurélien Bellet , Aymeric Dieuleveut
2021
Pré-publication, Document de travail hal-03498158 v1
Image document

Artemis: tight convergence guarantees for bidirectional compression in heterogeneous settings for federated learning

Constantin Philippenko , Aymeric Dieuleveut
2020
Pré-publication, Document de travail hal-04350055 v1
Image document

Stochastic approximation in Hilbert spaces

Aymeric Dieuleveut
Statistics [math.ST]. Université Paris sciences et lettres, 2017. English. ⟨NNT : 2017PSLEE059⟩
Thèse tel-01705522 v2