معرفی
Jonathan W. Siegel is an Assistant Professor in the Mathematics Department at Texas A&M University. He holds a PhD in Mathematics from UCLA (2018) under Prof. Russel Caflisch and was a postdoc at Penn State (2018–2022) under Prof. Jinchao Xu. His research focuses on approximation theory, mathematical foundations of neural networks, numerical methods for PDEs, and applications in materials science. He is supported by NSF grants (DMS-2424305, CCF-2205004) and an ONR MURI grant (N00014-20-1-2787).
Education:
- PhD in Mathematics, UCLA, 2018
- Postdoctoral Researcher, Penn State University, 2018–2022
Research interests span theoretical machine learning, numerical analysis, and computational materials science. He explores topics such as neural network expressivity, greedy algorithms for PDEs, and optimization techniques for scientific computing.
His work emphasizes the development of rigorous mathematical frameworks for deep learning methods and their application to real-world problems like materials property prediction.
Grants and Awards: NSF DMS-2424305, NSF CCF-2205004, ONR MURI N00014-20-1-2787.
Advising: Supervised 6 students, including collaborations with Jinchao Xu and Stephan Wojtowytsch. Courses taught include advanced graduate-level topics like the Mathematical Theory of Deep Learning and Approximation Methods.
