Peter Y. Lu

Office: Searle 202

I am a Schmidt AI in Science Fellow at the University of Chicago working at the intersection of physics and machine learning. My research interests include physics-informed machine learning and interpretable representational learning with applications in nonlinear dynamics, condensed matter physics, photonics, fluid dynamics, biophysics, and other areas. I aim to develop new computational methods for modeling and understanding physical systems with an emphasis on incorporating physics-informed priors and identifying relevant and interpretable latent representations.

I received a Ph.D. in Physics from MIT in 2022, and an A.B. in Physics and Mathematics from Harvard in 2016.

Selected Publications

  1. Training neural operators to preserve invariant measures of chaotic attractors
    (2023) — Accepted at NeurIPS 2023
  2. Discovering conservation laws using optimal transport and manifold learning
    Peter Y. Lu, Rumen Dangovski, and Marin Soljačić
    Nature Communications (2023)
  3. Q-Flow: Generative Modeling for Differential Equations of Open Quantum Dynamics with Normalizing Flows
    Owen M Dugan, Peter Y. Lu, Rumen Dangovski, Di Luo, and Marin Soljačić
    Proceedings of the 40th International Conference on Machine Learning (2023)
  4. Deep Learning for Bayesian Optimization of Scientific Problems with High-Dimensional Structure
    Transactions of Machine Learning Research (2022)
  5. Discovering sparse interpretable dynamics from partial observations
    Peter Y. Lu, Joan Ariño Bernad, and Marin Soljačić
    Communications Physics (2022)
  6. Discovering Dynamical Parameters by Interpreting Echo State Networks
    Oreoluwa Alao*, Peter Y. Lu*, and Marin Soljačić
    NeurIPS 2021 AI for Science Workshop (2021) — Best Paper Award
  7. Integration of Neural Network-Based Symbolic Regression in Deep Learning for Scientific Discovery
    Samuel Kim, Peter Y. Lu, Srijon Mukherjee, Michael Gilbert, Li Jing, Vladimir Čeperić, and Marin Soljačić
    IEEE Transactions on Neural Networks and Learning Systems (2021)
  8. Extracting Interpretable Physical Parameters from Spatiotemporal Systems Using Unsupervised Learning
    Peter Y. Lu, Samuel Kim, and Marin Soljačić
    Physical Review X (2020)
  9. Energy Loss at Propagating Jamming Fronts in Granular Gas Clusters
    Justin C. Burton, Peter Y. Lu, and Sidney R. Nagel
    Physical Review Letters (2013)