3 papers
cs.LG2026
Parameter-Free Dynamic Regret for Unconstrained Linear Bandits
Alberto Rumi, Andrew Jacobsen, Nicolò Cesa-Bianchi +1
We study dynamic regret minimization in unconstrained adversarial linear bandit problems. In this setting, a learner must minimize the cumulative loss relative to an arbitrary sequ…
cs.LG2025
Self-Directed Learning of Convex Labelings on Graphs
Georgy Sokolov, Maximilian Thiessen, Margarita Akhmejanova +2
We study the problem of classifying the nodes of a given graph in the self-directed learning setup. This learning setting is a variant of online learning, where rather than an adve…
cs.LG2024
Bandits with Abstention under Expert Advice
Stephen Pasteris, Alberto Rumi, Maximilian Thiessen +4
We study the classic problem of prediction with expert advice under bandit feedback. Our model assumes that one action, corresponding to the learner's abstention from play, has no…