Complexity Theoretic Limitations on Learning DNF’s
Amit Daniely, Shai Shalev‐Shwartz · 2016
Using the recently developed framework of [14], we show that under a natural assumption on the complexity of refuting random K-SAT formulas, learning DNF formulas is hard. Further-more, the same assumption implies the hardness of learning intersections of ω(log(n)) halfspaces, agnostically learning conjunctions, as well as virtually all (distribution free) learning problems that were previously shown hard (under complexity assumptions).