Emergent Mind
Complexity theoretic limitations on learning DNF's
(1404.3378)
Published Apr 13, 2014
in
cs.LG
and
cs.CC
Abstract
Using the recently developed framework of [Daniely et al, 2014], we show that under a natural assumption on the complexity of refuting random K-SAT formulas, learning DNF formulas is hard. Furthermore, the same assumption implies the hardness of learning intersections of $\omega(\log(n))$ halfspaces, agnostically learning conjunctions, as well as virtually all (distribution free) learning problems that were previously shown hard (under complexity assumptions).
We're not able to analyze this paper right now due to high demand.
Please check back later (sorry!).
Generate a summary of this paper on our Pro plan:
We ran into a problem analyzing this paper.