Mark Rhee

I'm a (applied) mathematics student at UC Berkeley with intended minors in computer science and philosophy. My interests lie at the intersection of fields such as math, computer science, physics, and philosophy. I'm particularly interested in the mathematical foundations of machine learning.

CV  /  LinkedIn  /  Github

profile photo

At Berkeley, I've taken a wide range of classes—mostly whatever I found interesting. You can find a list of all the (cool) classes I've taken so far and my thoughts on them here. I store notes and random musings here. Check it out if you want a peek into my brain.

Projects

Comparing Learning Dynamics of Gradient Descent and Muon optimizer
August 2025
Github Repo

Under construction.

Generalization Capabilities of Neural Network Substructure Ensembles
August 2025
Github Repo

Showed that ensembles of sparse subnetworks can vastly outperform dense networks while improving out-of-distribution generalization. This work highlights how sparsity and functional redundancy can be leveraged for more robust learning.

NBA Shot Prediction
December 2024
Github Repo

Predictive modeling of NBA shot success using features like shot distance and defender proximity. Trained logistic regression and neural networks. Features analysis by training models with individual variables.


Most of the source code for this website was borrowed from Jon Barron's website.