activity
20152026
most citedExact Worst-case Performance of First-order Methods for Composite Convex Optimization

109 citations · 280 across the 31 of their papers we have counts for

collaborators
Showing 2021Show all

6 papers · 1 filter

math.OC2021★ 3 cited

Super-Acceleration with Cyclical Step-sizes

Baptiste Goujaud, Damien Scieur, Aymeric Dieuleveut +2

We develop a convergence-rate analysis of momentum with cyclical step-sizes. We show that under some assumption on the spectral gap of Hessians in machine learning, cyclical step-s…

math.OC2021★ 1 cited

A Continuized View on Nesterov Acceleration for Stochastic Gradient Descent and Randomized Gossip

Mathieu Even, Raphaël Berthier, Francis Bach +5

We introduce the continuized Nesterov acceleration, a close variant of Nesterov acceleration whose variables are indexed by a continuous time parameter. The two variables continuou…

cs.DC2021

A Continuized View on Nesterov Acceleration

Raphaël Berthier, Francis Bach, Nicolas Flammarion +2

We introduce the "continuized" Nesterov acceleration, a close variant of Nesterov acceleration whose variables are indexed by a continuous time parameter. The two variables continu…

math.OC2021★ 1 cited

An optimal gradient method for smooth strongly convex minimization

Adrien Taylor, Yoel Drori

We present an optimal gradient method for smooth strongly convex optimization. The method is optimal in the sense that its worst-case bound on the distance to an optimal point exac…

math.OC2021

On the oracle complexity of smooth strongly convex minimization

Yoel Drori, Adrien Taylor

We construct a family of functions suitable for establishing lower bounds on the oracle complexity of first-order minimization of smooth strongly-convex functions. Based on this co…

math.OC2021★ 48 cited

Acceleration Methods

Alexandre d'Aspremont, Damien Scieur, Adrien Taylor

This monograph covers some recent advances in a range of acceleration techniques frequently used in convex optimization. We first use quadratic optimization problems to introduce t…