3 papers
math.OC2026
Sharp Dimension Dependence for the Last Iterate of the SubGradient Method
Guglielmo Beretta, Tommaso Cesari, Roberto Colomboni +1
We study the last iterate of the projected subGradient Method (sGM) for convex Lipschitz objectives defined on . We prove that, for a finite horizon and a constan…
math.OC2026
New Bounds for the Last Iterate of the Stochastic subGradient Method
Guglielmo Beretta, Tommaso Cesari, Roberto Colomboni +1
We study the last iterate of the stochastic subgradient method for one-dimensional convex Lipschitz objectives. For a fixed horizon , we consider the standard fixed stepsizes $Î…
cs.IT2026
Generalized Pinsker Inequality for Bregman Divergences of Negative Tsallis Entropies
Guglielmo Beretta, Tommaso Cesari, Roberto Colomboni
The Pinsker inequality lower bounds the Kullback--Leibler divergence in terms of total variation and provides a canonical way to convert control…