Students

I have been fortunate to advise and co-advise over 10 PhD student interns:

• Chaoran Cheng 2024
  • PhD Candidate in Computer Science, University of Illinois Urbana-Champaign
• Utkarsh . 2024
  • PhD Candidate in Computational Science and Engineering, MIT
• Luca Masserano 2024
  • PhD Candidate in Statistics and Machine Learning, Carnegie Mellon University
• Matthias Karlbauer 2023-2024
  • Comparing and Contrasting Deep Learning Weather Prediction Backbones on Navier-Stokes and Atmospheric Dynamics, AI4DifferentialEquations In Science ICLR Workshop, 2024.
  • PhD Candidate in Computer Science, University of Tübingen
• S Chandra Mouli 2023
  • Using Uncertainty Quantification to Characterize and Improve Out-of-Domain Learning for PDEs, ICML, 2024.
  • PhD Candidate in Computer Science, Purdue University
• Shikai Qiu 2023
  • Transferring Knowledge from Large Foundation Models to Small Downstream Models, ICML, 2024.
  • PhD Candidate in Computer Science, NYU Courant
• Derek Hansen 2022-2023
  • Learning Physical Models that Can Respect Conservation Laws, ICML, 2023.
  • PhD Candidate in Statistics and Scientific Computing, University of Michigan
  • Collaborated with Professor Michael W. Mahoney, University of California, Berkeley
• Nadim Saad 2021-2022
  • Guiding continuous operator learning through Physics-based boundary constraints, ICLR, 2023.
  • Modeling Advection on Directed Graphs using Matérn Gaussian Processes for Traffic Flow, Machine Learning and Physical Sciences NeurIPS Workshop, 2021.
  • PhD Candidate in Computational and Mathematical Engineering, Stanford University
• Xiyuan Zhang 2022-2023
  • First De-Trend then Attend: Rethinking Attention for Time-Series Forecasting, All Things Attention: Bridging Different Perspectives on Attention NeurIPS Workshop, 2022.
  • PhD Candidate in Computer Science and Engineering (CSE), University of California, San Diego
• Jiayao Zhang 2022-2023
  • Towards reverse causal inference on panel data: Precise formulation and challenges, A Causal View on Dynamical Systems NeurIPS Workshop, 2022.
  • PhD Candidate in Computer Science, University of Pennsylvania
• Mike Van Ness 2022
  • Cross-Frequency Time Series Meta-Forecasting, Technical Report, Preprint: arXiv:2302.02077, 2023.
  • PhD Candidate in Management Science and Engineering (MSE), Stanford University
• Ke Alexander Wang 2021
  • GOPHER: Categorical probabilistic forecasting with graph structure via local continuous-time dynamics, Spotlight at the ICBINB NeurIPS Workshop, PMLR, 2022.
  • PhD Candidate in Computer Science, Stanford University
• Kai Fung (Kelvin) Kan 2021
  • Learning Quantile Functions without Quantile Crossing for Distribution-free Time Series Forecasting, AISTATS, 2022.
  • PhD Candidate in Mathematics, Emory University
• Xiaoyong Jin, 2020-2022
  • Domain Adaptation for Time Series Forecasting via Attention Sharing, ICML, 2022.
  • PhD in Computer Science, University of California, Santa Barbara
• Rui (Ray) Wang 2020
  • Bridging Physics-based and Data-driven modeling for Learning Dynamical Systems, L4DC, 2021.
  • Contributed Talk, Best Paper Award at the NeurIPS, Machine Learning in Public Health NeurIPS Workshop, 2020.
  • PhD Candidate in Computer Science and Engineering (CSE), University of California, San Diego
  • Collaborated with Professors Rose Yu, University of California, San Diego and Christos Faloutsos, Carnegie Mellon University