3 papers
math.OC2026
Can Acceleration in Gradient-Norm Minimization Be Anytime? Sharp Last-Iterate Limits in Smooth Convex Optimization
Pierre Vernimmen, François Glineur
In smooth convex optimization, the gradient norm is a directly observable measure of stationarity. Accelerating a first-order method that minimizes the gradient norm is known to be…
math.OC2025
Empirical and computer-aided robustness analysis of long-step and accelerated methods in smooth convex optimization
Pierre Vernimmen, François Glineur
This work assesses both empirically and theoretically, using the performance estimation methodology, how robust different first-order optimization methods are when subject to relat…
math.OC2025
Worst-case convergence analysis of relatively inexact gradient descent on smooth convex functions
Pierre Vernimmen, François Glineur
We consider the classical gradient descent algorithm with constant stepsizes, where some error is introduced in the computation of each gradient. More specifically, we assume some…