Jerry Liu

  • Program Year: 1
  • Academic Institution: Stanford University
  • Field of Study: Computational Math
  • Academic Advisor: Jin Yao
  • Practicum(s): Practicum Not Yet Completed
  • Degree(s):
    B.S. Mathematics, and B.S. Computer Science, Duke University, 2022

Summary of Research

Modern machine learning, dominated by deep neural networks, has become a surprisingly empirical field -- the opacity of typical deep learning models makes interpreting their behavior difficult, and theory lags far behind practice when it comes to many modern innovations in neural network architecture design and training techniques.

I am interested in bridging the gap between the empirical effectiveness of modern deep learning and the provability/interpretability of classical perspectives from math and statistics. Recently, I am working on developing methods for solving inverse problems using deep generative models, in domains ranging from computational fluid dynamics to computer vision.

Publications

Jerry Liu, Jin Yao. Non-Diffusive Volume Advection with A High Order Interface Reconstruction Method. USNCCM, 2021.

Liu, J W, and Yao, J. Non-Diffusive Volume Advection with A High Order Interface Reconstruction Method. Lawrence Livermore National Laboratory, United States, 2021.

Jin Yao, Jerry Liu. Volume-of-Fluids Interface Reconstruction with Curvature and Corner Definition. WCCM-ECCOMAS, 2020.

Metaphor Detection Using Contextual Word Embeddings From Transformers, Second Workshop on Figurative Language Processing, NAACL, 2020. Jerry Liu, Nathan O' Hara, Alexander Rubin, Rachel Draelos, Cynthia Rudin.

Awards

Alex Vasilos Award, Duke University: 2022.
NSF Graduate Research Fellowship: 2022 (declined).
CRA Outstanding Undergraduate Researcher, honorable mention: 2022.
Phi Beta Kappa (honor society): 2021.
Karl Menger Award, Duke University: 2019.
William Lowell Putnam Mathematical Competition (top 250 participants): 2018, 2019.