Personal webpage*

Stephen Huan (浣苇杭)†

Abstract. I'm a PhD student in the Computer Science Department at Carnegie Mellon University, advised by Andrej Risteski and Nicholas Boffi. Prior to CMU, I was an undergraduate at Georgia Tech, where I worked on applied math with Florian Schäfer.

Key words. generative modeling, statistical inference, numerical computation

MSC codes. 68Q32, 62-08, 65F55

profile picture
A picture of the author.

1. Introduction. My research interests are in problems spanning machine learning, statistics, and applied mathematics. I'm particularly interested in designing efficient numerical algorithms for generative modeling, sampling, and statistical inference. See these high-level summaries for details about my work.

3. News.

Date Description
Giving a talk at CMU's Statistical Transport Talk Series. Thanks Siva for the invite!
Attending Supercomputing (SC) 26.
I am a teaching assistant for Andrej's new class 10-749 (AI for Scientific Computing).
At the Simons Institute's Diffusion Generative Modeling: Progress and Next Steps program.
Poster session at the DOE CSGF Annual Program Review.

References

[1]
S. Huan, A. Risteski, and Q. A. Wei, Mitigating error propagation in chaotic dynamics via inference-time noising: a view from backward sampling, submitted to STOC 2027.
pdf
[2]
S. Huan, J. Guinness, M. Katzfuss, H. Owhadi, and F. Schäfer, Sparse Inverse Cholesky Factorization of Dense Kernel Matrices by Greedy Conditional Selection, SIAM/ASA Journal on Uncertainty Quantification, 13 (2025), pp. 1649–1679, https://doi.org/10.1137/23M1606253.
arxiv blog code poster slides

*さみしいも、たのしい。Page source. Last updated: .

Funding: Department of Energy Computational Science Graduate Fellowship (DOE CSGF)

†Carnegie Mellon University, GHC 6221, 5000 Forbes Ave, Pittsburgh, PA 15213, slhuan@cs.cmu.edu, PGP: 0xEA6E27948C7DBF5D0DF085A10FBC2E3BA99DD60E, Corresponding Author

1