You could make a plot like Figure 1. Look for the turning point (do some calculu... | Hacker News

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

		RK on May 13, 2014 \| parent \| context \| favorite \| on: The Curse of Dimensionality in Classification You could make a plot like Figure 1. Look for the turning point (do some calculus if you can, i.e. d(perf)/d(dim) = 0).

christopheraden on May 14, 2014 | [–]

Derivatives require continuity. It would be sufficient to simply look at which number of dimensions gave you the best cross-validated classification rate.

mturmon on May 14, 2014 | [–]

Alas, it rarely looks clean like that. Actually never, in my experience, for real problems.

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