A hypothetical-context estimator is claimed to make Thompson Sampling minimax optimal for linear contextual bandits under arbitrary contexts, though the proof has a critical gap.
Abbasi-Yadkori, D
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Adaptive Data Augmentation for Thompson Sampling
A hypothetical-context estimator is claimed to make Thompson Sampling minimax optimal for linear contextual bandits under arbitrary contexts, though the proof has a critical gap.