232 citations · 453 across the 44 of their papers we have counts for
9 papers · 1 filter
Compression with Exact Error Distribution for Federated Learning
Mahmoud Hegazy, Rémi Leluc, Cheuk Ting Li +1
Compression schemes have been extensively used in Federated Learning (FL) to reduce the communication cost of distributed learning. While most approaches rely on a bounded variance…
On Fundamental Proof Structures in First-Order Optimization
Baptiste Goujaud, Aymeric Dieuleveut, Adrien Taylor
First-order optimization methods have attracted a lot of attention due to their practical success in many applications, including in machine learning. Obtaining convergence guarant…
Proving Linear Mode Connectivity of Neural Networks via Optimal Transport
Damien Ferbach, Baptiste Goujaud, Gauthier Gidel +1
The energy landscape of high-dimensional non-convex optimization problems is crucial to understanding the effectiveness of modern deep neural network architectures. Recent works ha…
Compressed and distributed least-squares regression: convergence rates with applications to Federated Learning
Constantin Philippenko, Aymeric Dieuleveut
In this paper, we investigate the impact of compression on stochastic gradient algorithms for machine learning, a technique widely used in distributed and federated learning. We un…
Provable non-accelerations of the heavy-ball method
Baptiste Goujaud, Adrien Taylor, Aymeric Dieuleveut
In this work, we show that the heavy-ball ($\HB$) method provably does not reach an accelerated convergence rate on smooth strongly convex problems. More specifically, we show that…
Conformal Prediction with Missing Values
Margaux Zaffran, Aymeric Dieuleveut, Julie Josse +1
Conformal prediction is a theoretically grounded framework for constructing predictive intervals. We study conformal prediction with missing values in the covariates -- a setting t…
Counter-examples in first-order optimization: a constructive approach
Baptiste Goujaud, Aymeric Dieuleveut, Adrien Taylor
While many approaches were developed for obtaining worst-case complexity bounds for first-order optimization methods in the last years, there remain theoretical gaps in cases where…
Stochastic Approximation Beyond Gradient for Signal Processing and Machine Learning
Aymeric Dieuleveut, Gersende Fort, Eric Moulines +1
Stochastic Approximation (SA) is a classical algorithm that has had since the early days a huge impact on signal processing, and nowadays on machine learning, due to the necessity…
Naive imputation implicitly regularizes high-dimensional linear models
Alexis Ayme, Claire Boyer, Aymeric Dieuleveut +1
Two different approaches exist to handle missing values for prediction: either imputation, prior to fitting any predictive algorithms, or dedicated methods able to natively incorpo…