I’m Ivan Belenko, a University of Washington undergraduate researching efficient optimizers and AI systems for the edge.
About me
Currently an undergraduate student at the University of Washington, completing a double major in computer science & mathematics.
Interested in Machine Learning and AI, specifically in deployment on the edge.
Currently working on optimizer research.
You can see some of my code on GitHub.
C++ · Python · LaTeX · HTML/CSS
PyTorch · NumPy · UNIX · Git · Vim · VS Code
English · Russian
Muon, a SOTA-level optimizer, takes a new approach toward optimization. By analyzing and hypothesizing how its mechanics work, one can try to design a similar optimizer from the same core ideas. Since Muon orthogonalizes 2D update matrices…
Read articleMy ongoing journey for learning Artificial Intelligence / Machine Learning using PyTorch and NumPy.
A website used as my portfolio written in python with Flask, hosted on an OCI instance using a Gunicorn WSGI server proxied to Caddy. All pages are markdown files served in html.
Coursework
