AI4Society Seminar - Lily Xu - Overcoming Uncertainty for Decision-Making in Planetary Health

Talk Abstract: Our planet faces growing crises including biodiversity loss, food insecurity, and public health risks, which compound and accelerate one another. Underlying these global challenges is the urgent need to effectively allocate scarce resources, often in dynamic environments with limited data. Many of these challenges can be modeled using Markov decision processes such as restless multi-armed bandits, which traditionally require a perfect model of the environment and relatively small problem sizes. We’ll explore how online learning, deep reinforcement learning, and mixed-integer programming can help overcome these challenges of missing data and complexity.

Speaker Bio: Lily Xu is an Assistant Professor at Columbia University, in the department of Industrial Engineering and Operations Research. She is a computer scientist developing AI methods across machine learning, optimization, and causal inference for planetary health challenges, particularly to address environmental challenges such as biodiversity conservation. Previously, she was a postdoc at the University of Oxford with the Leverhulme Centre for Nature Recovery, working with Alex Teytelboym, and received her PhD in computer science from Harvard University, advised by Milind Tambe. She co-directs the EAAMO research initiative, which advances computational techniques to improve access to opportunity for historically marginalized communities. Additionally, she partners closely with NGOs to bridge research and practice, serving as AI Lead for the SMART Partnership, where she helps build computational and research solutions for effective conservation management.