At least it will catch those valleys that are wider than the sampling resolution... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		cubefox 5 months ago \| parent \| context \| favorite \| on: Derivatives, Gradients, Jacobians and Hessians At least it will catch those valleys that are wider than the sampling resolution.

xigoi 5 months ago [–]

Yeah. The problem is that the number of samples needed is exponential in the dimension, so in a 1000-dimensional space, you won’t even be able to subdivide it into 2×…×2.

cubefox 5 months ago | [–]

Damn.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact