Showing 2025Show all
2 papers · 1 filter
cs.LG2025
Multicalibration Yields Better Matchings
Riccardo Colini Baldeschi, Simone Di Gregorio, Simone Fioravanti +9
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…
cs.LG2025
Online Learning in the Random Order Model
Martino Bernasconi, Andrea Celli, Riccardo Colini-Baldeschi +3
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 in…