We study satisficing regret minimization in bandits with knapsacks (BwK), where a learner sequentially selects randomized policies, i.e., distributions over arms, to obtain mean rewards above a satisficing threshold as frequently as possible while respecting finite resource budgets. The performance is measured by satis...
It is proved that PROBE is $\delta$-PAC and attains the known-correlation oracle sample complexity up to a constant multiplicative factor and a constant additive calibration cost and the guarantee extends to the $(\epsilon,\delta)$-PAC setting under minimal changes to the algorithm.
DASH is proposed, a Decoupled Adaptive Surrogate--Acquisition Harness for large-language- model (LLM)-enhanced AutoBO, which selects surrogates by predictive reliability, uncertainty calibration, and ranking consistency; its two-stage acquisition controller periodically reallocates quotas across acquisition functions,...
Changquan Zhao, Yuxiang Sun, Ruihao Zhu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
