Towards theory-guided, impact driven AI by Dr Davin Choo
Abstract
Many AI systems operate in structured, uncertain, and resource-limited environments. My research develops theory-guided methods for efficient learning and decision-making under such conditions, drawing from areas such as statistical modeling, algorithmic theory, causal reasoning, and reinforcement learning.
In this talk, I will outline my research vision, which revolves around three synergistic themes:
- Foundational AI/ML research, designing statistically and computationally efficient methods for structured distributions;
- Algorithms with imperfect advice, which formally incorporate resource-efficient information into provably optimal computer systems at scale;
- AI + X collaborations, where principled modeling and algorithmic insights drive measurable improvements in public health and decision sciences.
I will also discuss recent progress in each area and sketch ideas that lay the foundation for my future research agenda toward theory-guided, impact-driven AI.
Biography
Davin is a postdoctoral fellow at Teamcore, Harvard University. He earned his PhD in Computer Science from the National University of Singapore (NUS) as an AISG PhD fellow, a Master’s degree in Computer Science from ETH Zurich, and double First-Class Honours in Computer Science and Applied Mathematics from NUS. Between his undergraduate and Masters, he also worked for a while as an applied research scientist at DSO National Laboratories on projects at the intersection of AI and security. During his PhD at NUS, he focused on the foundations of AI and machine learning, working on statistical models, causal inference, and the design of resource-efficient algorithms. His current postdoctoral research at Harvard explores how principled modeling and AI techniques can be applied to real-world problems with the goal of achieving meaningful social impact