activity
20162022
most citedCommunication trade-offs for synchronized distributed SGD with large step size

18 citations · 43 across the 6 of their papers we have counts for

collaborators

10 papers

math.OC20221 cited

Quadratic minimization: from conjugate gradient to an adaptive Heavy-ball method with Polyak step-sizes

Baptiste Goujaud, Adrien Taylor, Aymeric Dieuleveut

In this work, we propose an adaptive variation on the classical Heavy-ball method for convex quadratic minimization. The adaptivity crucially relies on so-called "Polyak step-sizes…

math.OC20222 cited

Optimal first-order methods for convex functions with a quadratic upper bound

Baptiste Goujaud, Adrien Taylor, Aymeric Dieuleveut

We analyze worst-case convergence guarantees of first-order optimization methods over a function class extending that of smooth and convex functions. This class contains convex fun…

stat.ML202217 cited

Adaptive Conformal Predictions for Time Series

Margaux Zaffran, Aymeric Dieuleveut, Olivier Féron +2

Uncertainty quantification of predictive models is crucial in decision-making problems. Conformal prediction is a general and theoretically sound answer. However, it requires excha…

stat.ML2022

Minimax rate of consistency for linear models with missing values

Alexis Ayme, Claire Boyer, Aymeric Dieuleveut +1

Missing values arise in most real-world data sets due to the aggregation of multiple sources and intrinsically missing information (sensor failure, unanswered questions in surveys.…

cs.LG20205 cited

On Convergence-Diagnostic based Step Sizes for Stochastic Gradient Descent

Scott Pesme, Aymeric Dieuleveut, Nicolas Flammarion

Constant step-size Stochastic Gradient Descent exhibits two phases: a transient phase during which iterates make fast progress towards the optimum, followed by a stationary phase d…

math.ST2020

Debiasing Stochastic Gradient Descent to handle missing values

Julie Josse, Aude Sportisse, Claire Boyer +1

Stochastic gradient algorithm is a key ingredient of many machine learning methods, particularly appropriate for large-scale learning.However, a major caveat of large data is their…