Preprint in the OpenAI Math release
Projection moments, positive cap domination, and Riesz estimates on the sphere
OpenAI
Abstract
We prove moment estimates for exact random projections of finite measures whose mass is controlled on Euclidean balls, and derive positive domination by countable sums of spherical cap measures. For learners with bits of memory, these estimates give three proofs that uniform-sphere average success at least 2/3 at angular accuracy requires noiseless Gaussian observations. The three proofs keep their different stopping and accuracy costs explicit.
open until 1 Jan 2028
est. 50% chance this result is independently verified by the end of 2027.
Not verified 50%Verified 50%
What do you think this paper will get?
All positions stay anonymous.
Discussion (0)
Sign in to comment.