Publications

Full list also on Google Scholar. Preprints are on arXiv unless otherwise noted.

2026
Scalable Utility-Aware Multiclass Calibration
M. Hegazy, M.I. Jordan, A. Dieuleveut
AISTATS 2026 — Spotlight
Uncertainty quantification
PDF Conference
Tight Analysis of Decentralized SGD: A Markov Chain Perspective
L. Versini, P. Mangold, A. Dieuleveut
AISTATS 2026
Decentralized Stochastic approximation
PDF Conference
From Inexact Gradients to Byzantine Robustness: Acceleration and Optimization under Similarity
R. Gaucher, A. Dieuleveut, H. Hendrikx
Preprint, 2026
Decentralized Optimization
PDF Preprint
2025
Federated Majorize-Minimization: Beyond Parameter Aggregation
A. Dieuleveut, G. Fort, M. Hegazy, H.T. Wai
Preprint, 2025
Federated learning Stochastic approximation
PDF Preprint
Valid Selection among Conformal Sets
M. Hegazy, L. Aolaritei, M.I. Jordan, A. Dieuleveut
NeurIPS 2025
Uncertainty quantification
PDF Conference
Tight analyses of first-order methods with error feedback
D.B. Thomsen, A. Taylor, A. Dieuleveut
NeurIPS 2025
Optimization Federated learning
PDF Conference
Building Blocks of Differentially Private Training
M. Hegazy, A. Dieuleveut
ICLR Blogpost Track, 2025
Differential privacy Stochastic approximation
Blog Conference
Humanity's Last Exam
Center for AI Safety, Scale AI & HLE Contributors Consortium
Nature 649, 1139–1146, 2025
Member of the HLE Contributors Consortium. Contributed to the dataset.
Nature arXiv Journal
Open Problem: Two Riddles in Heavy-Ball Dynamics
B. Goujaud, A. Taylor, A. Dieuleveut
Preprint, 2025
Optimization
PDF Preprint
Scaffold with Stochastic Gradients: New Analysis with Linear Speed-Up
P. Mangold, A. Durmus, A. Dieuleveut, E. Moulines
ICML 2025
Federated learning Stochastic approximation
PDF Conference
Achieving Optimal Breakdown for Byzantine Robust Gossip
R. Gaucher, A. Dieuleveut, H. Hendrikx
ICML 2025
Decentralized Federated learning
PDF Conference
Refined Analysis of Constant Step Size Federated Averaging and Federated Richardson-Romberg Extrapolation
P. Mangold, A. Durmus, A. Dieuleveut, S. Samsonov, E. Moulines
AISTATS 2025
Federated learning Stochastic approximation
Proceedings Conference
Provable non-accelerations of the heavy-ball method
B. Goujaud, A. Taylor, A. Dieuleveut
Mathematical Programming, 2025
Optimization
PDF Journal
2024
Predictive Uncertainty Quantification with Missing Covariates
M. Zaffran, J. Josse, Y. Romano, A. Dieuleveut
Preprint, 2024
Uncertainty quantification Missing data
PDF Preprint
Byzantine-Robust Gossip: Insights from a Dual Approach
R. Gaucher, A. Dieuleveut, H. Hendrikx
Transactions on Machine Learning Research, 02/2025
Decentralized Federated learning
PDF Journal
Compressed and distributed least-squares regression: convergence rates with applications to Federated Learning
C. Philippenko, A. Dieuleveut
Journal of Machine Learning Research 25, 2024
Federated learning Stochastic approximation
JMLR Journal
Random features models: a way to study the success of naive imputation
A. Ayme, C. Boyer, A. Dieuleveut, E. Scornet
ICML 2024
Missing data
PDF Conference
Sliced-Wasserstein Estimation with Spherical Harmonics as Control Variates
R. Leluc, A. Dieuleveut, F. Portier, J. Segers, A. Zhuman
ICML 2024
Stochastic approximation
PDF Conference
Proving linear mode connectivity of neural networks via optimal transport
D. Ferbach, B. Goujaud, G. Gidel, A. Dieuleveut
AISTATS 2024
Optimization
PDF Conference
Compression with Exact Error Distribution for Federated Learning
M. Hegazy, R. Leluc, C.T. Li, A. Dieuleveut
AISTATS 2024
Federated learning Differential privacy
PDF Conference
2023
Stochastic Approximation Beyond Gradient for Signal Processing and Machine Learning
A. Dieuleveut, G. Fort, E. Moulines, H.T. Wai
IEEE Transactions on Signal Processing, 2023
Stochastic approximation
IEEE Journal
Conformal Prediction with Missing Values
M. Zaffran, A. Dieuleveut, J. Josse, Y. Romano
ICML 2023
Uncertainty quantification Missing data
PDF Conference
Naive imputation implicitly regularizes high-dimensional linear models
A. Ayme, C. Boyer, A. Dieuleveut, E. Scornet
ICML 2023
Missing data
PDF Conference
Counter-examples in first-order optimization: a constructive approach
B. Goujaud, A. Dieuleveut, A. Taylor
IEEE Control Systems Letters 7, 2485–2490
Optimization
PDF Journal
On fundamental proof structures in first-order optimization
B. Goujaud, A. Dieuleveut, A. Taylor
IEEE CDC 2023
Optimization
IEEE Conference
2022
Adaptive Conformal Predictions for Time Series
M. Zaffran, O. Féron, Y. Goude, J. Josse, A. Dieuleveut
ICML 2022
Uncertainty quantification Time series
PDF Conference
Minimax rate of consistency for linear models with missing values
A. Ayme, C. Boyer, A. Dieuleveut, E. Scornet
ICML 2022
Missing data
PDF Conference
PEPit: computer-assisted worst-case analyses of first-order optimization methods in Python
B. Goujaud, C. Moucer, F. Glineur, J. Hendrickx, A. Taylor, A. Dieuleveut
Mathematical Programming Computation 16 (3), 337–367, 2024
Optimization
PDF Code Journal
Quadratic minimization: from conjugate gradient to an adaptive Polyak's momentum method with Polyak step-sizes
B. Goujaud, A. Taylor, A. Dieuleveut
Open Journal of Mathematical Optimization 5, 1–10, 2024
Optimization
PDF Journal
Differentially Private Federated Learning on Heterogeneous Data
M. Noble, A. Bellet, A. Dieuleveut
AISTATS 2022
Federated learning Differential privacy
PDF Conference
QLSD: Quantised Langevin Stochastic Dynamics for Bayesian Federated Learning
M. Vono, V. Plassier, A. Durmus, A. Dieuleveut, E. Moulines
AISTATS 2022
Federated learning Stochastic approximation
PDF Conference
Super-Acceleration with Cyclical Step-sizes
B. Goujaud, D. Scieur, A. Dieuleveut, A. Taylor, F. Pedregosa
AISTATS 2022
Optimization Stochastic approximation
PDF Conference
FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings
J. Ogier du Terrail, S.-S. Ayed, E. Cyffers, F. Grimberg, C. He, R. Loeb, P. Mangold, T. Marchand, O. Marfoq, E. Mushtaq, B. Muzellec, C. Philippenko, S. Silva, M. Teleńczuk, S. Albarqouni, S. Avestimehr, A. Bellet, A. Dieuleveut, M. Jaggi, S.P. Karimireddy, M. Lorenzi, G. Neglia, M. Tommasi, M. Andreux
NeurIPS 2022
Federated learning
PDF Conference
2021
Federated Expectation Maximization with heterogeneity mitigation and variance reduction
A. Dieuleveut, G. Fort, E. Moulines, G. Robin
NeurIPS 2021
Federated learning Stochastic approximation
PDF Conference
Preserved central model for faster bidirectional compression in distributed settings
C. Philippenko, A. Dieuleveut
NeurIPS 2021
Federated learning
PDF Conference
2020
Debiasing Stochastic Gradient Descent to handle missing values
A. Sportisse, C. Boyer, A. Dieuleveut, J. Josse
NeurIPS 2020
Missing data Stochastic approximation
PDF Conference
On Convergence-Diagnostic based Step Sizes for Stochastic Gradient Descent
S. Pesme, A. Dieuleveut, N. Flammarion
ICML 2020
Stochastic approximation Optimization
PDF Conference
Context Mover's Distance & Barycenters: Optimal transport of contexts for building representations
S.P. Singh, A. Hug, A. Dieuleveut, M. Jaggi
AISTATS 2020
Stochastic approximation
PDF Conference
2019
Unsupervised Scalable Representation Learning for Multivariate Time Series
J.-Y. Franceschi, A. Dieuleveut, M. Jaggi
NeurIPS 2019
Stochastic approximation Time series
PDF Code Conference
Communication trade-offs for synchronized distributed SGD with large step size
A. Dieuleveut, K.K. Patel
NeurIPS 2019
Federated learning Stochastic approximation
PDF Conference
Bridging the Gap between Constant Step Size Stochastic Gradient Descent and Markov Chains
A. Dieuleveut, A. Durmus, F. Bach
Annals of Statistics, 2019
Stochastic approximation
IMS PDF Journal
2017 and before
Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression
A. Dieuleveut, N. Flammarion, F. Bach
Journal of Machine Learning Research 18 (101), 2017
Stochastic approximation
JMLR PDF Journal
Non-parametric Stochastic Approximation with Large Step Sizes
A. Dieuleveut, F. Bach
Annals of Statistics 44 (4), 2016
Stochastic approximation
IMS PDF Journal