Parameter-free near-optimal regret bounds for non-stationary infinite-armed bandits are achieved via a blackbox restart scheme and a randomized elimination algorithm that tracks only significant rotting shifts.
Lattimore and Szepesvári, 2020, Section 7.1), with some small modifications to account for the mild corruption (Definition 1)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Tracking Most Significant Shifts in Infinite-Armed Bandits
Parameter-free near-optimal regret bounds for non-stationary infinite-armed bandits are achieved via a blackbox restart scheme and a randomized elimination algorithm that tracks only significant rotting shifts.