8 citations · 40 across the 29 of their papers we have counts for
9 papers · 1 filter
The Last Iterate of the Projected Stochastic Subgradient Method Pays a Logarithm, Even in Dimension One
Guglielmo Beretta, Tommaso Cesari, Roberto Colomboni
We prove that the projected stochastic subgradient method with the standard anytime stepsizes can suffer expected last-iterate optimization error of order $(\log…
An Efficient Minimax-Optimal Algorithm for Adversarial -Set Bandits
Francesco Bacchiocchi, Tommaso Cesari, Roberto Colomboni
We study adversarial combinatorial bandits with -set actions, where at each round the learner selects out of items and observes only the aggregate loss of the selected i…
No Extra Signals Needed: The Uniform Price of Explainable Information Design
Francesco Bacchiocchi, Tommaso Cesari, Roberto Colomboni
In information design, an informed sender aims to influence a receiver's decision by committing to a signaling scheme. However, optimal signaling schemes often rely on randomizatio…
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…
Sharp Normalized Covariance Bounds and Constant-Stretch Correlated Sampling on the Hypersimplex
Tommaso Cesari, Roberto Colomboni
We establish the normalized covariance bound conjectured by Anari et al. (2026, Conjecture 3) for fixed-rank external-field measures. Let and . For $w\in(0,+\inf…
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 $η…
Two-Action Apple Tasting with Switching Costs
Tommaso Cesari, Roberto Colomboni
We study the two-action apple-tasting problem with switching costs against an oblivious adversary. In an equivalent normalized formulation, at each round the learner chooses betwee…
Optimal Gap-Dependent Regret for Private Stochastic Decision-Theoretic Online Learning
Tommaso Cesari, Roberto Colomboni
We study stochastic decision-theoretic online learning with full information and event-level pure differential privacy. A COLT open problem of Hu and Mehta asks to determine the op…
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…