Research

My research lies at the intersection of statistics and machine learning. I am especially interested in methods that support reliable learning and decision making when data are sequential, distributed, expensive to collect, or generated by adaptive algorithms.

Sequential Decision Making

I work on inference and evaluation problems for adaptive data collection procedures, including bandit algorithms and policy evaluation. A recurring theme is how to quantify uncertainty when the data distribution is shaped by previous decisions.

Bayesian Optimization

I study Bayesian optimization methods for expensive black-box systems, with applications involving collaboration, trustworthiness, and feedback from human experts or large language models.

Federated and Collaborative Learning

My work also studies statistical learning and optimization across distributed agents or institutions, where privacy, heterogeneity, and communication constraints shape what can be learned.

Experimental Design

I am interested in design strategies for estimating main effects and understanding black-box models efficiently, especially when direct model access is limited.

For a complete list of papers, please see Publications.