News for hackers. Stuff that matters.

A comment on E-means: 10x faster k-means at equal loss. Parent comment

Re:E-means: 10x faster k-means at equal loss by Luke2642 on Monday November 09, 2026 @04:30PM (#50432461)
My personal favourite is compressive sensing, sparse signals beat the Nyquist sampling limit, by what seems like an unbounded amount 1000x, 1000000x, etc, because all real world stuff we care about lives on a low dimensional manifold, so unlike the noise.
[ Parent | on HN ]
Re:E-means: 10x faster k-means at equal loss by CyberDildonics on Tuesday November 10, 2026 @07:38AM (#50439483)
Sampling above the nyquist sampling limit then representing it as something else is not beating the nyquist sampling limit, it's just compression.
[ Parent | on HN ]
Re:E-means: 10x faster k-means at equal loss by Luke2642 on Thursday November 12, 2026 @02:47AM (#50464225)
You mean below, not above?

It's not compression. Look it up, it's really cool. Random sampling in a sparse basis. Single pixel camera can reconstruct a 10MP image, etc.

[ Parent | on HN ]