5 papers
SCOPE: Cost-Efficient Model Selection for Compound AI Systems under Quality Constraints
Yiqian Huang, Shiqi Zhang, Tianyuan Jin +1
A compound AI system consists of multiple LLM modules, together handling complex and multi-step tasks that exceed the capabilities of a single model. Existing systems often use a s…
SteerConf: Steering LLMs for Confidence Elicitation
Ziang Zhou, Tianyuan Jin, Jieming Shi +1
Large Language Models (LLMs) exhibit impressive performance across diverse domains but often suffer from overconfidence, limiting their reliability in critical applications. We pro…
Optimal Batched Best Arm Identification
Tianyuan Jin, Yu Yang, Jing Tang +2
We study the batched best arm identification (BBAI) problem, where the learner's goal is to identify the best arm while switching the policy as less as possible. In particular, we…
Optimal Streaming Algorithms for Multi-Armed Bandits
Tianyuan Jin, Keke Huang, Jing Tang +1
This paper studies two variants of the best arm identification (BAI) problem under the streaming model, where we have a stream of arms with reward distributions supported on $[…
Optimal Batched Linear Bandits
Xuanfei Ren, Tianyuan Jin, Pan Xu
We introduce the E algorithm for the batched linear bandit problem, incorporating an Explore-Estimate-Eliminate-Exploit framework. With a proper choice of exploration rate, we…