A parameter-free algorithm for online learning with noisy side observations via weighted graphs achieves regret of order square root of effective independence number times T.
Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Online learning with noisy side observations
A parameter-free algorithm for online learning with noisy side observations via weighted graphs achieves regret of order square root of effective independence number times T.