Mars (Liyao) Gao

photo_mars

Ph.D. student
Paul G. Allen School of Computer Science & Engineering
University of Washington

News

[Apr. 2025] Upcoming invited talk @ UCSB. New
[Apr. 2025] Upcoming talk @ UW CS4Env. New
[Mar. 2025] Our newest work "Sparse identification of nonlinear dynamics and Koopman operators with Shallow Recurrent Decoder Networks" with isotropic flow and convex loss landscape visualization is now available on arXiv! [Website] [Colab] [Github] New
[Oct. 2024] Invited talk @ Georgia Tech ACMS seminar.
[Mar. 2024] Our paper "Bayesian autoencoders for data-driven discovery of coordinates, governing equations, and fundamental constants," is now published in PRSA!

About me

I am currently a Ph.D. student in the Paul G. Allen School of Computer Science & Engineering at the University of Washington. I am very fortunate to be advised by Professor J. Nathan Kutz on sparse regression and deep learning methods for equation discovery. I am passionate about developing generalizable and interpretable learning frameworks that address practical challenges and enhance our understanding of the world. My interests include deep learning, statistical learning theory, and Bayesian methods. I aspire to apply these techniques to solve complex scientific problems in real-world scenarios.

Selected publications

photo_prsa 

Bayesian autoencoders for data-driven discovery of coordinates, governing equations and fundamental constants.
Mars L. Gao, J. Nathan Kutz.
Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

photo_pami 

Convergence of uncertainty estimates in ensemble and Bayesian sparse model discovery.
Mars L. Gao, Urban Fasel, Steven L. Brunton, J. Nathan Kutz.
In submission.

photo_tmlr 

Deformation Robust Roto-Scale-Translation Equivariant CNNs.
Mars L. Gao, Wei Zhu, Guang Lin.
Transaction of Machine Learning Research.

Contact

Email: marsgao [at] uw [dot] edu