First worst-case regret bounds of Õ(m√(NT)) for CTS-G in sleeping semi-bandits with matching lower bound, plus CL-SG variant achieving Õ(√(mNT)) with matching lower bound.
Bridging the Regret Gap in Combinatorial Thompson Sampling: Worst-Case Guarantees and Algorithmic Refine- ment
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
extension 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
extension 1polarities
extend 1representative citing papers
citing papers explorer
-
Worst-Case Regret Bounds for Combinatorial Thompson Sampling in Sleeping Semi-Bandits
First worst-case regret bounds of Õ(m√(NT)) for CTS-G in sleeping semi-bandits with matching lower bound, plus CL-SG variant achieving Õ(√(mNT)) with matching lower bound.