Aymeric Dieuleveut

59 papers A* 15A 7Journal 35Unranked 2

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Byzantine-Robust Gossip: Insights from a Dual Approach. Trans. Mach. Learn. Res. Renaud Gaucher, Hadrien Hendrikx, Aymeric Dieuleveut
2026	J	`jnl`	From Inexact Gradients to Byzantine Robustness: Acceleration and Optimization under Similarity. CoRR Renaud Gaucher, Aymeric Dieuleveut, Hadrien Hendrikx
2026	J	`jnl`	Tight Analysis of Decentralized SGD: A Markov Chain Perspective. CoRR Lucas Versini, Paul Mangold, Aymeric Dieuleveut
2025	J	`jnl`	Federated Majorize-Minimization: Beyond Parameter Aggregation. CoRR Aymeric Dieuleveut, Gersende Fort, Mahmoud Hegazy, Hoi-To Wai
2025	A	`conf`	Refined Analysis of Constant Step Size Federated Averaging and Federated Richardson-Romberg Extrapolation. AISTATS Paul Mangold, Alain Oliviero Durmus, Aymeric Dieuleveut, Sergey Samsonov, Eric Moulines
2025	A*	`conf`	Scaffold with Stochastic Gradients: New Analysis with Linear Speed-Up. ICML Paul Mangold, Alain Oliviero Durmus, Aymeric Dieuleveut, Eric Moulines
2025	J	`jnl`	Scaffold with Stochastic Gradients: New Analysis with Linear Speed-Up. CoRR Paul Mangold, Alain Durmus, Aymeric Dieuleveut, Eric Moulines
2025	J	`jnl`	Scalable Utility-Aware Multiclass Calibration. CoRR Mahmoud Hegazy, Michael I. Jordan, Aymeric Dieuleveut
2025	J	`jnl`	Tight analyses of first-order methods with error feedback. CoRR Daniel Berg Thomsen, Adrien B. Taylor, Aymeric Dieuleveut
2025	A*	`conf`	Unified Breakdown Analysis for Byzantine Robust Gossip. ICML Renaud Gaucher, Aymeric Dieuleveut, Hadrien Hendrikx
2025	J	`jnl`	Valid Selection among Conformal Sets. CoRR Mahmoud Hegazy, Liviu Aolaritei, Michael I. Jordan, Aymeric Dieuleveut
2024	J	`jnl`	Byzantine-Robust Gossip: Insights from a Dual Approach. CoRR Renaud Gaucher, Hadrien Hendrikx, Aymeric Dieuleveut
2024	J	`jnl`	Compressed and distributed least-squares regression: convergence rates with applications to federated learning. J. Mach. Learn. Res. Constantin Philippenko, Aymeric Dieuleveut
2024	A	`conf`	Compression with Exact Error Distribution for Federated Learning. AISTATS Mahmoud Hegazy, Rémi Leluc, Cheuk Ting Li, Aymeric Dieuleveut
2024	J	`jnl`	PEPit: computer-assisted worst-case analyses of first-order optimization methods in Python. Math. Program. Comput. Baptiste Goujaud, Céline Moucer, François Glineur, Julien M. Hendrickx, Adrien B. Taylor, Aymeric Dieuleveut
2024	A	`conf`	Proving Linear Mode Connectivity of Neural Networks via Optimal Transport. AISTATS Damien Ferbach, Baptiste Goujaud, Gauthier Gidel, Aymeric Dieuleveut
2024	A*	`conf`	Random features models: a way to study the success of naive imputation. ICML Alexis Ayme, Claire Boyer, Aymeric Dieuleveut, Erwan Scornet
2024	J	`jnl`	Refined Analysis of Federated Averaging's Bias and Federated Richardson-Romberg Extrapolation. CoRR Paul Mangold, Alain Durmus, Aymeric Dieuleveut, Sergey Samsonov, Eric Moulines
2024	J	`jnl`	Short Paper - Quadratic minimization: from conjugate gradient to an adaptive Polyak's momentum method with Polyak step-sizes. Open J. Math. Optim. Baptiste Goujaud, Adrien B. Taylor, Aymeric Dieuleveut
2024	A*	`conf`	Sliced-Wasserstein Estimation with Spherical Harmonics as Control Variates. ICML Rémi Leluc, Aymeric Dieuleveut, François Portier, Johan Segers, Aigerim Zhuman
2024	J	`jnl`	Sliced-Wasserstein Estimation with Spherical Harmonics as Control Variates. CoRR Rémi Leluc, Aymeric Dieuleveut, François Portier, Johan Segers, Aigerim Zhuman
2023	J	`jnl`	Compressed and distributed least-squares regression: convergence rates with applications to Federated Learning. CoRR Constantin Philippenko, Aymeric Dieuleveut
2023	J	`jnl`	Compression with Exact Error Distribution for Federated Learning. CoRR Mahmoud Hegazy, Rémi Leluc, Cheuk Ting Li, Aymeric Dieuleveut
2023	A*	`conf`	Conformal Prediction with Missing Values. ICML Margaux Zaffran, Aymeric Dieuleveut, Julie Josse, Yaniv Romano
2023	J	`jnl`	Conformal Prediction with Missing Values. CoRR Margaux Zaffran, Aymeric Dieuleveut, Julie Josse, Yaniv Romano
2023	J	`jnl`	Counter-Examples in First-Order Optimization: A Constructive Approach. IEEE Control. Syst. Lett. Baptiste Goujaud, Aymeric Dieuleveut, Adrien B. Taylor
2023	A*	`conf`	Naive imputation implicitly regularizes high-dimensional linear models. ICML Alexis Ayme, Claire Boyer, Aymeric Dieuleveut, Erwan Scornet
2023	—	`conf`	On Fundamental Proof Structures in First-Order Optimization. CDC Baptiste Goujaud, Aymeric Dieuleveut, Adrien B. Taylor
2023	J	`jnl`	Proving Linear Mode Connectivity of Neural Networks via Optimal Transport. CoRR Damien Ferbach, Baptiste Goujaud, Gauthier Gidel, Aymeric Dieuleveut
2023	J	`jnl`	Stochastic Approximation Beyond Gradient for Signal Processing and Machine Learning. IEEE Trans. Signal Process. Aymeric Dieuleveut, Gersende Fort, Eric Moulines, Hoi-To Wai
2022	A*	`conf`	Adaptive Conformal Predictions for Time Series. ICML Margaux Zaffran, Olivier Féron, Yannig Goude, Julie Josse, Aymeric Dieuleveut
2022	J	`jnl`	Adaptive Conformal Predictions for Time Series. CoRR Margaux Zaffran, Aymeric Dieuleveut, Olivier Féron, Yannig Goude, Julie Josse
2022	A	`conf`	Differentially Private Federated Learning on Heterogeneous Data. AISTATS Maxence Noble, Aurélien Bellet, Aymeric Dieuleveut
2022	A*	`conf`	FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings. NeurIPS Jean Ogier du Terrail, Samy-Safwan Ayed, Edwige Cyffers, Felix Grimberg, Chaoyang He, Regis Loeb, Paul Mangold, Tanguy Marchand, Othmane Marfoq, Erum Mushtaq, Boris Muzellec, Constantin Philippenko, Santiago Silva, Maria Telenczuk, Shadi Albarqouni, Salman Avestimehr, Aurélien Bellet, Aymeric Dieuleveut, Martin Jaggi, Sai Praneeth Karimireddy, Marco Lorenzi, Giovanni Neglia, Marc Tommasi, Mathieu Andreux
2022	J	`jnl`	FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings. CoRR Jean Ogier du Terrail, Samy-Safwan Ayed, Edwige Cyffers, Felix Grimberg, Chaoyang He, Regis Loeb, Paul Mangold, Tanguy Marchand, Othmane Marfoq, Erum Mushtaq, Boris Muzellec, Constantin Philippenko, Santiago Silva, Maria Telenczuk, Shadi Albarqouni, Salman Avestimehr, Aurélien Bellet, Aymeric Dieuleveut, Martin Jaggi, Sai Praneeth Karimireddy, Marco Lorenzi, Giovanni Neglia, Marc Tommasi, Mathieu Andreux
2022	J	`jnl`	Minimax rate of consistency for linear models with missing values. CoRR Alexis Ayme, Claire Boyer, Aymeric Dieuleveut, Erwan Scornet
2022	A*	`conf`	Near-optimal rate of consistency for linear models with missing values. ICML Alexis Ayme, Claire Boyer, Aymeric Dieuleveut, Erwan Scornet
2022	J	`jnl`	PEPit: computer-assisted worst-case analyses of first-order optimization methods in Python. CoRR Baptiste Goujaud, Céline Moucer, François Glineur, Julien M. Hendrickx, Adrien B. Taylor, Aymeric Dieuleveut
2022	A	`conf`	QLSD: Quantised Langevin Stochastic Dynamics for Bayesian Federated Learning. AISTATS Maxime Vono, Vincent Plassier, Alain Durmus, Aymeric Dieuleveut, Eric Moulines
2022	A	`conf`	Super-Acceleration with Cyclical Step-sizes. AISTATS Baptiste Goujaud, Damien Scieur, Aymeric Dieuleveut, Adrien B. Taylor, Fabian Pedregosa
2021	J	`jnl`	Differentially Private Federated Learning on Heterogeneous Data. CoRR Maxence Noble, Aurélien Bellet, Aymeric Dieuleveut
2021	J	`jnl`	Federated Expectation Maximization with heterogeneity mitigation and variance reduction. CoRR Aymeric Dieuleveut, Gersende Fort, Eric Moulines, Geneviève Robin
2021	A*	`conf`	Federated-EM with heterogeneity mitigation and variance reduction. NeurIPS Aymeric Dieuleveut, Gersende Fort, Eric Moulines, Geneviève Robin
2021	A*	`conf`	Preserved central model for faster bidirectional compression in distributed settings. NeurIPS Constantin Philippenko, Aymeric Dieuleveut
2021	J	`jnl`	Preserved central model for faster bidirectional compression in distributed settings. CoRR Constantin Philippenko, Aymeric Dieuleveut
2021	J	`jnl`	QLSD: Quantised Langevin stochastic dynamics for Bayesian federated learning. CoRR Maxime Vono, Vincent Plassier, Alain Durmus, Aymeric Dieuleveut, Eric Moulines
2020	J	`jnl`	Artemis: tight convergence guarantees for bidirectional compression in Federated Learning. CoRR Constantin Philippenko, Aymeric Dieuleveut
2020	A	`conf`	Context Mover's Distance & Barycenters: Optimal Transport of Contexts for Building Representations. AISTATS Sidak Pal Singh, Andreas Hug, Aymeric Dieuleveut, Martin Jaggi
2020	A*	`conf`	Debiasing Averaged Stochastic Gradient Descent to handle missing values. NeurIPS Aude Sportisse, Claire Boyer, Aymeric Dieuleveut, Julie Josse
2020	A*	`conf`	On Convergence-Diagnostic based Step Sizes for Stochastic Gradient Descent. ICML Scott Pesme, Aymeric Dieuleveut, Nicolas Flammarion
2020	J	`jnl`	On Convergence-Diagnostic based Step Sizes for Stochastic Gradient Descent. CoRR Scott Pesme, Aymeric Dieuleveut, Nicolas Flammarion
2019	A*	`conf`	Communication trade-offs for Local-SGD with large step size. NeurIPS Aymeric Dieuleveut, Kumar Kshitij Patel
2019	J	`jnl`	Communication trade-offs for synchronized distributed SGD with large step size. CoRR Kumar Kshitij Patel, Aymeric Dieuleveut
2019	—	`conf`	Context Mover's Distance & Barycenters: Optimal transport of contexts for building representations. DGS@ICLR Sidak Pal Singh, Andreas Hug, Aymeric Dieuleveut, Martin Jaggi
2019	A*	`conf`	Unsupervised Scalable Representation Learning for Multivariate Time Series. NeurIPS Jean-Yves Franceschi, Aymeric Dieuleveut, Martin Jaggi
2019	J	`jnl`	Unsupervised Scalable Representation Learning for Multivariate Time Series. CoRR Jean-Yves Franceschi, Aymeric Dieuleveut, Martin Jaggi
2018	J	`jnl`	Wasserstein is all you need. CoRR Sidak Pal Singh, Andreas Hug, Aymeric Dieuleveut, Martin Jaggi
2017	J	`jnl`	Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression. J. Mach. Learn. Res. Aymeric Dieuleveut, Nicolas Flammarion, Francis R. Bach
2016	J	`jnl`	Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression. CoRR Aymeric Dieuleveut, Nicolas Flammarion, Francis R. Bach