Aymeric Dieuleveut | DeepAI

AI Chat

Featured Co-authors

Francis Bach
160 publications
Martin Jaggi
104 publications
Eric Moulines
63 publications
Alain Durmus
51 publications
Aurélien Bellet
50 publications
Nicolas Flammarion
44 publications
Yaniv Romano
35 publications
Hoi-To Wai
34 publications
Julie Josse
31 publications
Erwan Scornet
23 publications
Claire Boyer
19 publications

∙ 08/02/2023

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

In this paper, we investigate the impact of compression on stochastic gr...

0 Constantin Philippenko, et al. ∙

∙ 06/05/2023

Conformal Prediction with Missing Values

Conformal prediction is a theoretically grounded framework for construct...

0 Margaux Zaffran, et al. ∙

∙ 02/22/2023

Stochastic Approximation Beyond Gradient for Signal Processing and Machine Learning

Stochastic approximation (SA) is a classical algorithm that has had sinc...

0 Aymeric Dieuleveut, et al. ∙

∙ 01/31/2023

Naive imputation implicitly regularizes high-dimensional linear models

Two different approaches exist to handle missing values for prediction: ...

0 Alexis Ayme, et al. ∙

∙ 02/15/2022

Adaptive Conformal Predictions for Time Series

Uncertainty quantification of predictive models is crucial in decision-m...

0 Margaux Zaffran, et al. ∙

∙ 02/03/2022

Minimax rate of consistency for linear models with missing values

Missing values arise in most real-world data sets due to the aggregation...

0 Alexis Ayme, et al. ∙

∙ 01/11/2022

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

PEPit is a Python package aiming at simplifying the access to worst-case...

0 Baptiste Goujaud, et al. ∙

∙ 11/17/2021

Differentially Private Federated Learning on Heterogeneous Data

Federated Learning (FL) is a paradigm for large-scale distributed learni...

0 Maxence Noble, et al. ∙

∙ 11/03/2021

Federated Expectation Maximization with heterogeneity mitigation and variance reduction

The Expectation Maximization (EM) algorithm is the default algorithm for...

0 Aymeric Dieuleveut, et al. ∙

∙ 06/01/2021

QLSD: Quantised Langevin stochastic dynamics for Bayesian federated learning

Federated learning aims at conducting inference when data are decentrali...

0 Maxime Vono, et al. ∙

∙ 02/24/2021

Preserved central model for faster bidirectional compression in distributed settings

We develop a new approach to tackle communication constraints in a distr...

0 Constantin Philippenko, et al. ∙

∙ 07/01/2020

On Convergence-Diagnostic based Step Sizes for Stochastic Gradient Descent

Constant step-size Stochastic Gradient Descent exhibits two phases: a tr...

0 Scott Pesme, et al. ∙

∙ 06/25/2020

Artemis: tight convergence guarantees for bidirectional compression in Federated Learning

We introduce a new algorithm - Artemis - tackling the problem of learnin...

0 Constantin Philippenko, et al. ∙

∙ 02/21/2020

Debiasing Stochastic Gradient Descent to handle missing values

A major caveat of large scale data is their incom-pleteness. We propose ...

0 Aude Sportisse, et al. ∙

∙ 04/25/2019

Communication trade-offs for synchronized distributed SGD with large step size

Synchronous mini-batch SGD is state-of-the-art for large-scale distribut...

0 Kumar Kshitij Patel, et al. ∙

∙ 01/30/2019

Unsupervised Scalable Representation Learning for Multivariate Time Series

Time series constitute a challenging data type for machine learning algo...

0 Jean-Yves Franceschi, et al. ∙

∙ 08/29/2018

Wasserstein is all you need

We propose a unified framework for building unsupervised representations...

0 Sidak Pal Singh, et al. ∙

∙ 07/20/2017

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

We consider the minimization of an objective function given access to un...

0 Aymeric Dieuleveut, et al. ∙

∙ 02/17/2016

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

We consider the optimization of a quadratic objective function whose gra...

0 Aymeric Dieuleveut, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world