Research interests
My research explores new frontiers of data-driven decision making — reinforcement learning in particular — with applications to digital interventions such as mobile health. A few highlights of my work:
- Sample-efficient online algorithm design. Sample efficiency is crucial in data-scarce domains like mobile health. I develop algorithms that leverage structural information to improve sample efficiency [I, II, III].
- Statistical inference for adaptively collected data. Adaptive experimental designs, commonly used in mobile health, introduce dependencies across time and users that challenge existing inference methods. I develop approaches that remain valid in these settings [I, II].
- Transfer and multitask learning. Limited sample sizes in mobile health often make it necessary to transfer knowledge from existing datasets, but domain shifts — participant demographics, intervention designs, societal changes — complicate this. I design transfer learning approaches that account for such shifts [I, II, III, IV, V].
