Welcome

I am Co-director of Princeton AI for Accelerated Invention and associate professor at the Center for Statistics and Machine Learning, Department of Electrical and Computer Engineering, and by courtesy, Department of Computer Science and the Omenn-Darling Bioengineering Institute at Princeton University. I am also affiliated with the Princeton ML Theory Group and Princeton Language+Intelligence Initiative, and I was a visiting research scientist at DeepMind, Institute of Advanced Studies, and Simons Institute on Theoretical Computer Science. I got my PhD in Electrical Engineering and Computer Science with a minor in Math from MIT in 2013, where I worked with Dimitri P. Bertsekas at the Laboratory for Information and Decision Systems (now IDSS). Before that, I did my undergraduate in Tsinghua University. My group works on machine learning and optimization for decision making in complex systems. In particular, we are interested in:

  • Machine learning theory, such as understanding exploration in online interactive learning, statistical limits for reinforcement learning, representation learning, diffusion models.
  • Developing RL and generative AI algorithms leveraging problem structures with provable generalizability, robustness and adaptivity.
  • AI applications in healthcare, biotech, drug discovery, fintech and intelligent systems. We are also interested in understanding theoretically how ML can accelerate scientific discoveries.

[My Bio (updated July 2024)]

Openings available for undergrad interns, visitors and postdoc fellows. Feel free to email your cv and representative publications to mengdiw@princeton.edu if you are interested in our research.