Yuxin Ma
PhD Student, Johns Hopkins University
Hi! I am a fourth year PhD student at the Department of Applied Mathematics and Statistics at Johns Hopkins University, where I am fortunate to be advised by Soledad Villar and Tim Kunisky. My research interests lie in developing a better understanding of neural networks using a variety of mathematical tools, including algebra, geometry, and probability. The topics I’m interested in include:
- Symmetries and equivariant machine learning
- Size generalization (training on small inputs, hope to perform well on large inputs)
- Hyperparameter transfer (tuning on small neural networks, use on large ones)
- Scaling limits (infinite width/depth limit) of neural networks
- Random matrix theory and low-rank recovery
Check out the about me page to learn more!
Previously, I completed an MMath and BA Hons degree in Mathematics at the University of Cambridge where I was mentored by Benedikt Löwe and Orsola Rath Spivack. During my master’s studies, I focused on statistics and completed an essay on Topological Data Analysis, advised by John Aston and Jacob Rasmussen.