Mengfan Xu

Assistant Professor at UMass Amherst.

Github.JPG

324 ELab, Engineering Lab 1

160 Governors Drive

Amherst, MA, 01003, U.S.A.

Contact: mengfanxu@umass.edu

Hi! I am Mengfan, and I am a tenure-track assistant professor in the Department of Mechanical and Industrial Engineering at UMass Amherst. I recently obtained my Ph.D. from the Department of Industrial Engineering and Management Sciences at Northwestern University, where I am very fortunate and grateful to be advised by Prof. Diego Klabjan. Previously, I obtained my Bachelor’s degree in Statistics from University of Science and Technology of China (USTC) in 2018.

My research interests lie at the intersection of Operations Research and Machine Learning. My research goal is to formulate online sequential decision-making problems and subsequently develop algorithms that are provably optimal for addressing them, with a particular emphasis on Multi-armed Bandits. What I am aiming for is to capture the intricate dynamics within the underlying structures with new methodologies, driven by real world problems faced by decision makers and with applications accross a wide range of domains. In general, my research interests are as follows:

  • Multi-armed Bandit and Reinforcement Learning
  • Sequential decision making under uncertainty
  • Algorithm design
  • Statistical Learning
  • Stochastic processes/optimization
  • e-Commerce
  • Causal Inference

news

Mar, 2024 I am happy to share that I will be joining the Department of Mechanical and Industrial Engineering at the University of Massachusetts Amherst as a tenure-track assistant professor starting September 2024! :sparkles: :heart:
Sep, 2023 I am happy to share that our paper, titled “Decentralized Randomly Distributed Multi-agent Multi-armed Bandit with Heterogeneous Rewards”, has been accepted at NeurIPS 2023 as a Spotlight! :sparkles: :heart:
Aug, 2023 I am happy to share that our abstract, titled “Multi-agent and Multi-objective Multi-armed Bandit”, will be presented at Informs Annual Meeting on Oct. 17th in Phoenix, AZ!
Apr, 2023 I am happy to share that our paper, titled “Pareto Regret Analyses in Multi-objective Multi-armed Bandit”, has been accepted at ICML 2023! :sparkles: :heart: