Matteo Castiglioni

Breaking the $T^{3/4}$ Barrier for Regret Minimization With Bi-Dimensional CDFs

Matteo Castiglioni, Anna Lunghi, Alberto Marchesi

We study regret minimization for learning CDF-related objectives of the form \[ g(x)\cdot\mathbb{P}_{X\sim\mathcal{D}}(X\le x), \] over $[0, 1]^{2}$ , where $g$ is a known Lipschitz fu…

Toward Optimal Regret in Robust Pricing: Decoupling Corruption and Time

Kalana Kalupahana, Francesco Emanuele Stradi, Matteo Castiglioni +1

We design the first regret guarantees for robust dynamic pricing that decouple the dependence on the corruption $C$ and the time horizon $T$ . In dynamic pricing, a seller with unli…

Multi-Armed Bandits With Best-Action Queries

Francesco Bacchiocchi, Matteo Castiglioni, Alberto Marchesi +1

We study \emph{multi-armed bandits} (MABs) augmented with \emph{best-action queries}, in which the learner may additionally query an oracle that reveals the best arm in the current…

Replicable Constrained Bandits

Matteo Bollini, Gianmarco Genalti, Francesco Emanuele Stradi +2

Algorithmic \emph{replicability} has recently been introduced to address the need for reproducible experiments in machine learning. A \emph{replicable online learning} algorithm is…

Truly Adapting to Adversarial Constraints in Constrained MABs

Francesco Emanuele Stradi, Kalana Kalupahana, Matteo Castiglioni +2

We study the constrained variant of the \emph{multi-armed bandit} (MAB) problem, in which the learner aims not only at minimizing the total loss incurred during the learning dynami…

cs.LG2026★ 1 cited

The Sample Complexity of Uniform Approximation for Multi-Dimensional CDFs and Fixed-Price Mechanisms

Matteo Castiglioni, Anna Lunghi, Alberto Marchesi

We study the sample complexity of learning a uniform approximation of an $n$ -dimensional cumulative distribution function (CDF) within an error $ε > 0$ , when observations are restri…

Beyond Slater's Condition in Online CMDPs with Stochastic and Adversarial Constraints

Francesco Emanuele Stradi, Eleonora Fidelia Chiefari, Matteo Castiglioni +2

We study \emph{online episodic Constrained Markov Decision Processes} (CMDPs) under both stochastic and adversarial constraints. We provide a novel algorithm whose guarantees great…

Data-Dependent Regret Bounds for Constrained MABs

Gianmarco Genalti, Francesco Emanuele Stradi, Matteo Castiglioni +2

This paper initiates the study of data-dependent regret bounds in constrained MAB settings. These bounds depend on the sequence of losses that characterize the problem instance. Th…

No-Regret Learning Under Adversarial Resource Constraints: A Spending Plan Is All You Need!

Francesco Emanuele Stradi, Matteo Castiglioni, Alberto Marchesi +2

We study online decision making problems under resource constraints, where both reward and cost functions are drawn from distributions that may change adversarially over time. We f…

Nearly-Optimal Bandit Learning in Stackelberg Games with Side Information

Maria-Florina Balcan, Martino Bernasconi, Matteo Castiglioni +3

We study the problem of online learning in Stackelberg games with side information between a leader and a sequence of followers. In every round the leader observes contextual infor…

Optimal Strong Regret and Violation in Constrained MDPs via Policy Optimization

Francesco Emanuele Stradi, Matteo Castiglioni, Alberto Marchesi +1

We study online learning in \emph{constrained MDPs} (CMDPs), focusing on the goal of attaining sublinear strong regret and strong cumulative constraint violation. Differently from…

Best-of-Both-Worlds Policy Optimization for CMDPs with Bandit Feedback

Francesco Emanuele Stradi, Anna Lunghi, Matteo Castiglioni +2

We study online learning in constrained Markov decision processes (CMDPs) in which rewards and constraints may be either stochastic or adversarial. In such settings, Stradi et al.(…

Beyond Primal-Dual Methods in Bandits with Stochastic and Adversarial Constraints

Martino Bernasconi, Matteo Castiglioni, Andrea Celli +1

We address a generalization of the bandit with knapsacks problem, where a learner aims to maximize rewards while satisfying an arbitrary set of long-term constraints. Our goal is t…

No-Regret is not enough! Bandits with General Constraints through Adaptive Regret Minimization

Martino Bernasconi, Matteo Castiglioni, Andrea Celli

In the bandits with knapsacks framework (BwK) the learner has $m$ resource-consumption (packing) constraints. We focus on the generalization of BwK in which the learner has a set o…

Learning Constrained Markov Decision Processes With Non-stationary Rewards and Constraints

Francesco Emanuele Stradi, Anna Lunghi, Matteo Castiglioni +2

In constrained Markov decision processes (CMDPs) with adversarial rewards and constraints, a well-known impossibility result prevents any algorithm from attaining both sublinear re…