No algorithm can be optimal in both stochastic and adversarial best-arm identification; a new parameter-free algorithm matches the derived lower bound up to log factors in stochastic cases while handling adversarial rewards.
Selection of learning experts https://ieeexplore.ieee.org/document/7965962/
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Best of both worlds: Stochastic & adversarial best-arm identification
No algorithm can be optimal in both stochastic and adversarial best-arm identification; a new parameter-free algorithm matches the derived lower bound up to log factors in stochastic cases while handling adversarial rewards.