Answers are grounded in this paper and cite their sources.
We show that replacing LinUCB's usual confidence width $β$ by any fixed $α>0$ preserves sublinear regret when the action set is M-smooth and m-strongly convex. Our high-probability regret bound for this generalisation, $α$-LinUCB, establishes that valid confidence sets are not necessary for the success of LinUCB. We identify the mechanism behind this result: action-set curvature drives $α$-LinUCB to explore every direction, even when optimism is not guaranteed. To analyse this mechanism, we introduce a logarithmically capped spectral potential that, unlike the standard log-determinant potential, caps contributions from well-explored directions. This yields lower bounds on the smallest eigenvalue of the design matrix. At the standard confidence width α=β√dlog T, our T-round regret bound in d dimensions is O(M/md√Tlog T), up to iterated-logarithmic factors, improving the horizon dependence of the classical LinUCB guarantee by a factor of √log T.
No takes yet. Share an insight, caveat, or question.
Yahmed et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: