Hello World

Hello world!

I study theoretical and applied machine learning - learning efficiency, concept representation, and information compression. My work sits at the intersection of statistical learning theory and machine learning systems.

My intuition is that theoretical models can extend to empirical results and that informative answers come from abstracting experimental conclusions into concrete theorems and proofs. The problems I find the most interesting incorporate both theory and applications: how do models develop representations during training? Can these representations be learned more efficiently or compressed? What properties of the data and model determine what is learned? How do the representations that empirical research uncover relate to the scaling behavior that learning theory models?

One of the many joys of machine learning research is the compatibility of theory and experimentation. Theoretical ideas can be cheaply tested (relatively speaking) on widely accessible hardware without bureaucratic processes. This solves an important problem: too many theoretical ideas yield zero practical applications, and many experiments produce unexplainable results. The ability to quantify tangible outcomes and connect these observations to mathematical foundations provides computer scientists with a unique ability: to simplify the complexity of the universe's boundless information.

This blog was inspired by the extraordinary academic contributions of professors, researchers, and podcasters. I aspire to impart even a fraction of scientific contribution as these giants of machine learning research.

This page is meant to be an in-progress notebook. Candidly, I expect some of my conjectures to be incorrect and revised. These posts are merely ideas that I am still trying to formalize and organize into deeper theories. The overall goal is to make the research availible to the wider scientific community. Nonetheless, I will attempt to make these ideas as well developed as possible (and limit the use of LLMs in my writing).

These notes are written for other researchers interested in machine learning, though I hope they remain accessible to anyone curious about theoretical learning and why machine learning systems behave the way they do. If something here is useful (or wrong), I would be glad to hear about it. Progress on these questions is not an individual undertaking; we all stand on the shoulders of giants.

Thanks for reading.