best-arm-identification

Tag

Cards List
#best-arm-identification

Dynamically Allocating Evaluation Effort for Model Ranking

arXiv cs.CL · 2026-08-05 Cached

This paper formalizes multi-model human evaluation as a best-arm identification problem in a multi-armed bandit setup, adaptively allocating annotation effort to focus on competitive models and improve ranking discrimination.

0 favorites 0 likes
#best-arm-identification

Best-Arm Identification with Generative Proxy

arXiv cs.LG · 2026-07-09 Cached

This paper studies fixed-confidence best-arm identification where costly reward observations are paired with cheap but correlated proxy scores from generative models. It proposes the PROBE algorithm that uses control-variate adjustment and upper certificates on residual variance to achieve oracle-like sample complexity.

0 favorites 0 likes
#best-arm-identification

Best Arm Identification in Generalized Linear Bandits via Hybrid Feedback

arXiv cs.AI · 2026-05-08 Cached

This paper introduces a hybrid Track-and-Stop algorithm for best arm identification in generalized linear bandits that unifies absolute and relative feedback. The authors propose a likelihood-ratio-based confidence sequence to adaptively allocate queries, demonstrating improved sample efficiency over baseline methods.

0 favorites 0 likes
← Back to home

Submit Feedback