For heavy-tailed piecewise-stationary bandits, this paper presents a Catoni-style change-point detector and a UCB-style algorithm whose regret matches a claimed lower bound up to logarithmic factors.
Piecewise stationary bandits under risk criteria
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Catoni-Style Change Point Detection for Regret Minimization in Non-Stationary Heavy-Tailed Bandits
For heavy-tailed piecewise-stationary bandits, this paper presents a Catoni-style change-point detector and a UCB-style algorithm whose regret matches a claimed lower bound up to logarithmic factors.