Image of Haoxuan Chen

Ph.D. Candidate
ICME, Stanford

Office: Huang Engineering Center, 475 Via Ortega Suite B060 (064A), Stanford, CA 94305
Email: haoxuanc [at] stanford [dot] edu
Languages:
English, Mandarin
Programming:
Python, Julia, C++, JAVA, MATLAB, R, Mathematica

I am currently a third year Ph.D. Candidate at the Institute for Computational and Mathematical Engineering (ICME) of Stanford University, where I am extremely fortunate to be advised by Professor Lexing Ying (Mathematics, ICME). I am also privileged to collaborate with Professor Jose H. Blanchet (Management Science and Engineering, ICME) and Professor Grant M. Rotskoff (Theoretical Chemistry, ICME) on certain projects.

Before coming to Stanford, I obtained my Bachelor of Science from California Institute of Technology (Caltech), where I double majored Mathematics (Physics, Mathematics and Astronomy) and Information & Data Sciences (Computing and Mathematical Sciences). During my time at Caltech, I was very glad to have Professor Andrew M. Stuart (Computing and Mathematical Sciences) as my undergraduate research supervisor. In summer 2021, I was a visiting undergraduate researcher at the Uncertainty Quantification Group of Massachusetts Institute of Technology (MIT), where I was very lucky to be hosted by Professor Youssef M. Marzouk (Aeronautics and Astronautics, Computational Science and Engineering).

My current research interests lie in the intersection of scientific machine learning (AI4Science), learning theory and statistics, numerical analysis and scientific computing (computational physics and chemistry). Please check out my Google Scholar and OpenReview to learn more about my research!

Special thanks go to all my friends and collaborators, especially Yifan Chen, Yiping Lu, Yinuo Ren and Qizheng Zhang (in no particular order), who have all generously provided many constructive suggestions and help when I make this website.

News

  • Our latest work on the theoretical analysis of discrete diffusion models is now online (arXiv link)! Please check it out! (2024.10)
  • Our paper on the mathematical theory of reducing the inference cost for diffusion models via parallel sampling just got accepted as a Spotlight Poster at NeurIPS 2024! Feel free to check it out (arXiv link)! (2024.09)