5 papers
ShoppingComp: Are LLMs Really Ready for Your Shopping Cart?
Huaixiao Tou, Ying Zeng, Yuemeng Li +6
We present ShoppingComp, a challenging real-world benchmark for comprehensively evaluating LLM-powered shopping agents on three core capabilities: precise product retrieval, expert…
Learning bounds for doubly-robust covariate shift adaptation
Jeonghwan Lee, Cong Ma
Distribution shift between the training domain and the test domain poses a key challenge for modern machine learning. An extensively studied instance is the \emph{covariate shift},…
The Adaptivity Barrier in Batched Nonparametric Bandits: Sharp Characterization of the Price of Unknown Margin
Rong Jiang, Cong Ma
We study batched nonparametric contextual bandits under a margin condition when the margin parameter is unknown. To capture the statistical cost of this ignorance, we introduc…
Batched Nonparametric Contextual Bandits
Rong Jiang, Cong Ma
We study nonparametric contextual bandits under batch constraints, where the expected reward for each action is modeled as a smooth function of covariates, and the policy updates a…
Auditing Differential Privacy in the Black-Box Setting
Kaining Shi, Cong Ma
This paper introduces a novel theoretical framework for auditing differential privacy (DP) in a black-box setting. Leveraging the concept of -differential privacy, we explicitly…