Tianyu Wang

I'm Tianyu Wang. I'm a PhD candidate at Duke CS advised by Prof. Cynthia Rudin. My research focuses on (general) bandit learning (my take of general bandit learning). In the long run, I'm particularly interested in

  1. robust bandit learning (that handles singularities, non-commutativeness in the space, etc.) (P1).

  2. bandit learning in strongly motivated settings. (P2).

My email address is tianyu AT cs DOT duke DOT edu.

Some recent publications/preprints

Bandits for BMO Functions, ICML, 2020 (bib|pdf), note: related to (P1)

Tianyu Wang and Cynthia Rudin


Center for Data Science, Zhejiang University

Bandit Learning with New Feedback Structures, Dec 22, 2020

Fudan University/Shanghai Center for Mathematical Sciences

Bandit Learning with New Feedback Structures, Dec 16, 2020

INFORMS 2020 Annual Meeting

Bandits for BMO Functions, In invited session: Recent Developments in Multi-Armed Bandits and Reinforcement Learning for Online Experiments