A hedged mixture of Cover and Robbins betting strategies on bounded data yields O(ln n) worst-case regret and almost-sure O(ln ln n) regret on typical paths, witnessing a sharp game-theoretic LIL.
Optimal best-arm identification methods for tail-risk measures
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
-
Cover meets Robbins while Betting on Bounded Data: $\ln n$ Regret and Almost Sure $\ln\ln n$ Regret
A hedged mixture of Cover and Robbins betting strategies on bounded data yields O(ln n) worst-case regret and almost-sure O(ln ln n) regret on typical paths, witnessing a sharp game-theoretic LIL.