원문 초록
We show that replacing LinUCB's usual confidence width $\beta$ by any fixed $\alpha>0$ preserves sublinear regret when the action set is $M$-smooth and $m$-strongly convex. Our high-probability regret bound for this generalisation, $\alpha$-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 $\alpha$-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 $\alpha=\beta\asymp\sqrt{d\log T}$, our $T$-round regret bound in $d$ dimensions is $O\bigl(\frac{M}{m}d\sqrt{T\log T}\bigr)$, up to iterated-logarithmic factors, improving the horizon dependence of the classical LinUCB guarantee by a factor of $\sqrt{\log T}$.
제출 이력
확인된 버전만 표시합니다. 전체 제출 이력은 arXiv 원문에서 확인하세요.
- arXiv:2611.04641v1제출 시각 미확인
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
공통 태그로 연결된 공개 논문이 아직 없습니다.
토론
이 논문과 연결된 포럼 글이 아직 없습니다.