Every Direction Holds a Line Without ee‑Random Points
Researchers proved that for every direction there exists a line with no double‑exponential random (ee‑random) points, settling a question posed by Lutz and Lutz in 2015. Read more: getnews.me/every-direction-holds-a-... #algorithmicrandomness #kakeya
A Kakeya set is the smallest space a cat can spin in every direction.
That’s your ReLU network.
Track those spins, and you get tighter control than PAC-Bayes.
Cats don’t take random walks. Neither should your optimizer.
#CatsOfML #Kakeya #CSTheory
PAC-Bayes tells you where the cat’s been.
Kakeya tells you where it can go.
We use cone crossings and directional bounds to track optimizer paths. Tighter than PAC-Bayes. No flat priors.
Wanna know how?
New ADAM paper drops soon.
#CatsOfML #Kakeya #OptimizerTheory #CSTheory
Nomen est omen: Joshua ZAHL 🔢 co-author of #Kakeya proof. Splendidly explained by @teorth.bsky.social.
@picanumeros.bsky.social @gaussianos.bsky.social @todos-math.bsky.social @mathematiguy.bsky.social
33-year-old mathematician Wang Hong from the Courant Institute of Mathematical Sciences (CIMS-NYU) has proved the century-old Kakeya conjecture in three dimensions with collaborator Joshua Zahl!
#Kakeya #KakeyaConjecture #ThreeDimensions #WangHong #CIMS #NYU #Conjecture #CenturyOldConjecture
