5 citations · 11 across the 6 of their papers we have counts for
4 papers · 1 filter
Principled Analyses and Design of First-Order Methods with Inexact Proximal Operators
Mathieu Barré, Adrien Taylor, Francis Bach
Proximal operations are among the most common primitives appearing in both practical and theoretical (or high-level) optimization methods. This basic operation typically consists i…
Complexity Guarantees for Polyak Steps with Momentum
Mathieu Barré, Adrien Taylor, Alexandre d'Aspremont
In smooth strongly convex optimization, knowledge of the strong convexity parameter is critical for obtaining simple methods with accelerated rates. In this work, we study a class…
Polyak Steps for Adaptive Fast Gradient Method
Mathieu Barré, Alexandre d'Aspremont
Accelerated algorithms for minimizing smooth strongly convex functions usually require knowledge of the strong convexity parameter . In the case of an unknown , current adapt…
An M* Proxy for Sparse Recovery Performance
Mathieu Barré, Alexandre d'Aspremont
This paper provides a new tractable lower bound for the sparse recovery threshold of sensing matrices. This lower bound is used as a proxy to quantify the quality of sensing matric…