Complexity theoretic limitations on learning DNF's

Amit Daniely; Shai Shalev-Shwartz

Complexity theoretic limitations on learning DNF's

The Rachel and Selim Benin School of Engineering and Computer Science

Research output: Contribution to journal › Conference article › peer-review

55 Scopus citations

Abstract

Using the recently developed framework of Daniely et al. (2014), we show that under a natural assumption on the complexity of random K-SAT, learning DNF formulas is hard. Furthermore, the same assumption implies the hardness of various learning problems, including intersections of ω(log(n)) halfspaces, agnostically learning conjunctions, as well as virtually all (distribution free) learning problems that were previously shown hard (under various complexity assumptions).

Original language	English
Pages (from-to)	815-830
Number of pages	16
Journal	Journal of Machine Learning Research
Volume	49
State	Published - 6 Jun 2016
Event	29th Conference on Learning Theory, COLT 2016 - New York, United States Duration: 23 Jun 2016 → 26 Jun 2016

Bibliographical note

Publisher Copyright:
© 2016 A. Daniely & S. Shalev-Shwartz.

Keywords

DNFs
Hardness of learning

Cite this

@article{acf9da36dced4e209ae8ae1e6bd2afd5,

title = "Complexity theoretic limitations on learning DNF's",

abstract = "Using the recently developed framework of Daniely et al. (2014), we show that under a natural assumption on the complexity of random K-SAT, learning DNF formulas is hard. Furthermore, the same assumption implies the hardness of various learning problems, including intersections of ω(log(n)) halfspaces, agnostically learning conjunctions, as well as virtually all (distribution free) learning problems that were previously shown hard (under various complexity assumptions).",

keywords = "DNFs, Hardness of learning",

author = "Amit Daniely and Shai Shalev-Shwartz",

note = "Publisher Copyright: {\textcopyright} 2016 A. Daniely \& S. Shalev-Shwartz.; 29th Conference on Learning Theory, COLT 2016 ; Conference date: 23-06-2016 Through 26-06-2016",

year = "2016",

month = jun,

day = "6",

language = "אנגלית",

volume = "49",

pages = "815--830",

journal = "Journal of Machine Learning Research",

issn = "1532-4435",

publisher = "Microtome Publishing",

}

TY - JOUR

T1 - Complexity theoretic limitations on learning DNF's

AU - Daniely, Amit

AU - Shalev-Shwartz, Shai

PY - 2016/6/6

Y1 - 2016/6/6

N2 - Using the recently developed framework of Daniely et al. (2014), we show that under a natural assumption on the complexity of random K-SAT, learning DNF formulas is hard. Furthermore, the same assumption implies the hardness of various learning problems, including intersections of ω(log(n)) halfspaces, agnostically learning conjunctions, as well as virtually all (distribution free) learning problems that were previously shown hard (under various complexity assumptions).

AB - Using the recently developed framework of Daniely et al. (2014), we show that under a natural assumption on the complexity of random K-SAT, learning DNF formulas is hard. Furthermore, the same assumption implies the hardness of various learning problems, including intersections of ω(log(n)) halfspaces, agnostically learning conjunctions, as well as virtually all (distribution free) learning problems that were previously shown hard (under various complexity assumptions).

KW - DNFs

KW - Hardness of learning

UR - https://www.scopus.com/pages/publications/105015544125

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.conferencearticle???

AN - SCOPUS:105015544125

SN - 1532-4435

VL - 49

SP - 815

EP - 830

JO - Journal of Machine Learning Research

JF - Journal of Machine Learning Research

T2 - 29th Conference on Learning Theory, COLT 2016

Y2 - 23 June 2016 through 26 June 2016

ER -

Complexity theoretic limitations on learning DNF's

Abstract

Bibliographical note

Keywords

Other files and links

Fingerprint

Cite this