Riccardo Colini Baldeschi — accepted AI-conference papers

2026

Multicalibration Yields Better Matchings

Riccardo Colini Baldeschi, Simone Di Gregorio, Simone Fioravanti, Federico Fusco, Ido Guy, Daniel Haimovich +6

ICML 2026poster

Consider the problem of finding the best matching in a weighted graph where we only have access to predictions of the actual stochastic weights, based on an underlying context. If the predictor is the Bayes optimal one, then computing the best matching based on the predicted weights is optimal. Howe…

Cited by 0 Source ↗Scholar ↗

2025

Online Learning in the Random-Order Model

Martino Bernasconi, Andrea Celli, Riccardo Colini Baldeschi, Federico Fusco, Stefano Leonardi, Matteo Russo

ICML 2025poster

In the random-order model for online learning, the sequence of losses is chosen upfront by an adversary and presented to the learner after a random permutation. Any random-order input is *asymptotically* equivalent to a stochastic i.i.d.~one, but, for finite times, it may exhibit significant *non-st…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Online Learning with Sublinear Best-Action Queries

Matteo Russo, Andrea Celli, Riccardo Colini Baldeschi, Federico Fusco, Daniel Haimovich, Dima Karamshuk +2

NeurIPS 2024poster

In online learning, a decision maker repeatedly selects one of a set of actions, with the goal of minimizing the overall loss incurred. Following the recent line of research on algorithms endowed with additional predictive features, we revisit this problem by allowing the decision maker to acquire a…

Cited by 1 Source ↗PDF ↗Scholar ↗