About Me

Hi, I’m Yifan!

I’m a fifth-year PhD student at Northwestern University. I’m advised by Prof. Jason Hartline. I received my B.S. in Computer Science from Peking University in 2020, where I was advised by Prof. Yuqing Kong.

I have a broad interest in theoretical computer science and economics. Recently, I aim at building a decision-theoretic framework for trustworthy AI.

My Research

My research emphasizes the fundamental decision-making value of AI through decision theory, the bedrock of game theory. The abstraction of a decision problem aligns closely with the modern “predict-then-optimize” workflow. In the workflow, upstream AI predictions are provided as a service to downstream decision-making, instead of designed for an application. The separation of prediction and decision-making arises from the increasing complexity of both AI and decision-making. My approach evaluates predictors out of the context of a particular application.

At the core of my techniques is proper scoring rules, the class of functions that evaluate a probabilistic prediction by the decision payoff it leads to, in the ``predict-then-optimize’’ workflow. My research focuses on the evaluation of trustworthy AI-assisted decision-making and algorithm design that enables trustworthiness. Currently, my research topics include information elicitation, calibration, and theoretical benchmarks for human-AI interaction.

News

🔥 I’m co-organizing the FOCS ‘24 Workshop on Calibration. The workshop will be coordinated with the Fall 2024 IDEAL Special Program on Interpretability, Privacy, and Fairness.