19 papers
Breaking the 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 , where is a known Lipschitz fu…
Beyond Slater's Condition in Online CMDPs with Stochastic and Adversarial Constraints
Francesco Emanuele Stradi, Eleonora Fidelia Chiefari, Matteo Castiglioni +2
The paper proposes a new online algorithm for episodic constrained Markov decision processes that achieves sublinear regret and constraint violation without assuming Slater's condi…
Online Resource Allocation With General Constraints
Eleonora Fidelia Chiefari, Francesco Emanuele Stradi, Matteo Castiglioni +1
Online resource allocation (ORA) is a fundamental framework for sequential decision-making problems under budget constraints, with applications ranging from online advertising to r…
Regret Minimization in Bilateral Trade With Perturbed Markets
Anna Lunghi, Matteo Castiglioni, Alberto Marchesi
We address the problem of maximizing Gain from Trade (GFT) in repeated buyer-seller exchanges subject to global budget balance constraints. While this problem is well-understood in…
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 -dimensional cumulative distribution function (CDF) within an error , when observations are restr…
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 and the time horizon . In dynamic pricing, a seller with unli…