Majority-of-Three is Optimal [arXiv]
How simple can an optimal learner be?
TLDRs
These are (hopefully) more high-level writeups of my research, intended to require little to no background in machine learning or theory. I started writing these mostly to get better at explaining things without defaulting to heavy math; to that end, these writeups are mostly meant to provide intuition and the main ideas, not exact mechanics. Comments and suggestions are more than welcome :).
A full list of work is at research.
3️⃣
🔇
Rao-Blackwellized Score Matching on Manifolds [arXiv]
What do generative modeling techniques actually recover, and can we do it better?