activity
20232025
most citedExact convergence rate of the last iterate in subgradient methods

1 citations · 1 across the 6 of their papers we have counts for

collaborators

6 papers

math.OC2025

On the Convex Interpolation for Linear Operators

Nizar Bousselmi, Zhicheng Deng, Jie Lu +2

The worst-case performance of an optimization method on a problem class can be analyzed using a finite description of the problem class, known as interpolation conditions. In this…

math.OC2025

Numerical Design of Optimized First-Order Algorithms

Yassine Kamri, Julien M. Hendrickx, François Glineur

We derive several numerical methods for designing optimized first-order algorithms in unconstrained convex optimization settings. Our methods are based on the Performance Estimatio…

math.OC2025

On the Worst-Case Analysis of Cyclic Block Coordinate Descent type Algorithms

Yassine Kamri, François Glineur, Julien M. Hendrickx +1

We study the worst-case behavior of Block Coordinate Descent (BCD) type algorithms for unconstrained minimization of coordinate-wise smooth convex functions. This behavior is indee…

math.OC2024

Comparison of Proximal First-Order Primal and Primal-Dual algorithms via Performance Estimation

Nizar Bousselmi, Nelly Pustelnik, Julien M. Hendrickx +1

Selecting the fastest algorithm for a specific signal/image processing task is a challenging question. We propose an approach based on the Performance Estimation Problem framework…

math.OC2024

On the Set of Possible Minimizers of a Sum of Convex Functions

Moslem Zamani, François Glineur, Julien M. Hendrickx

Consider a sum of convex functions, where the only information known about each individual summand is the location of a minimizer. In this work, we give an exact characterization o…

math.OC20231 cited

Exact convergence rate of the last iterate in subgradient methods

Moslem Zamani, François Glineur

We study the convergence of the last iterate in subgradient methods applied to the minimization of a nonsmooth convex function with bounded subgradients. We first introduce a proof…