← Authors

Aymeric Dieuleveut

24 papers · 2017–2025 · 4 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (10) 🌈 Renaissance Researcher (6) 🧭 Keyword Pioneer πŸƒ Academic Marathon (8) πŸ—ΊοΈ Taxonomy Completionist (14) 🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (4) πŸ† Keyword Champion (3) πŸ‘₯ Mega-Team (24) πŸ—ƒοΈ Keyword Collector (87) πŸ’Ž Century Club (24) πŸ”₯ Unstoppable (7) πŸ“ˆ Trend Setter ⚑ Prolific Year (5)

Conferences

ICML (9) AISTATS (7) NIPS (6) JMLR (2)

Top co-authors

Claire Boyer (4) Eric Moulines (4) Julie Josse (3) Constantin Philippenko (3) Martin Jaggi (3) Erwan Scornet (3) Paul Mangold (3) Alexis Ayme (3) Alain Oliviero Durmus (2) RΓ©mi Leluc (2)

Research topics

Differential Privacy (1) Statistics (1)

Keywords

distributed learning (6) stochastic gradient descent (6) federated learning (5) convergence rate (3) missing value (3) communication compression (2) differential privacy (2) prediction interval (2) conformal prediction (2) unsupervised learning (2) variance reduction (2) least squares regression (2) stochastic gradient (2) uncertainty quantification (2) convergence analysis (2) optimal transport (2) wasserstein distance (2) representation learning (2) gradient descent (2) linear regression (2)

Papers

Refined Analysis of Constant Step Size Federated Averaging and Federated Richardson-Romberg Extrapolation AISTATS 2025
Scaffold with Stochastic Gradients: New Analysis with Linear Speed-Up ICML 2025
Unified Breakdown Analysis for Byzantine Robust Gossip ICML 2025
Compressed and distributed least-squares regression: convergence rates with applications to federated learning JMLR 2024
Compression with Exact Error Distribution for Federated Learning AISTATS 2024
Proving Linear Mode Connectivity of Neural Networks via Optimal Transport AISTATS 2024
Random features models: a way to study the success of naive imputation ICML 2024
Sliced-Wasserstein Estimation with Spherical Harmonics as Control Variates ICML 2024
Conformal Prediction with Missing Values ICML 2023
Naive imputation implicitly regularizes high-dimensional linear models ICML 2023
Super-Acceleration with Cyclical Step-sizes AISTATS 2022
Differentially Private Federated Learning on Heterogeneous Data AISTATS 2022
Near-optimal rate of consistency for linear models with missing values ICML 2022
Adaptive Conformal Predictions for Time Series ICML 2022
FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings NIPS 2022
QLSD: Quantised Langevin Stochastic Dynamics for Bayesian Federated Learning AISTATS 2022
Federated-EM with heterogeneity mitigation and variance reduction NIPS 2021
Preserved central model for faster bidirectional compression in distributed settings NIPS 2021
Context Mover’s Distance & Barycenters: Optimal Transport of Contexts for Building Representations AISTATS 2020
Debiasing Averaged Stochastic Gradient Descent to handle missing values NIPS 2020
On Convergence-Diagnostic based Step Sizes for Stochastic Gradient Descent ICML 2020
Unsupervised Scalable Representation Learning for Multivariate Time Series NIPS 2019
Communication trade-offs for Local-SGD with large step size NIPS 2019
Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression JMLR 2017