A hybrid-feedback Track-and-Stop algorithm for best-arm identification in generalized linear bandits achieves δ-correctness with explicit stopping-time bounds and improved sample efficiency over baselines.
Then ϕ⋆(·) is continuous at θ⋆, and W ⋆(θ⋆) is convex, compact, and nonempty
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Best Arm Identification in Generalized Linear Bandits via Hybrid Feedback
A hybrid-feedback Track-and-Stop algorithm for best-arm identification in generalized linear bandits achieves δ-correctness with explicit stopping-time bounds and improved sample efficiency over baselines.