Years and Authors of Summarized Original Work
1997; Jackson
2005; Bshouty, Mossel, O’Donnell, Servedio
2009; Kalai, Samorodnitsky, Teng
Problem Definition
A disjunctive normal form (DNF) expression is a Boolean expression written as a disjunction of terms, where each term is the conjunction of Boolean variables that may or may not be negated. For example, \((v_{1} \wedge \overline{v_{2}}) \vee (v_{2} \wedge v_{3})\) is a two-term DNF expression over three variables. DNF expressions occur frequently in digital circuit design, where DNF is often referred to as sum of products notation. From a learning perspective, DNF expressions are of interest because they provide a natural representation for certain types of expert knowledge. For example, the conditions under which complex tax rules apply can often be readily represented as DNFs. Another nice property of DNF expressions is their universality: every n-bit Boolean function (the type of function considered in this entry unless otherwise...
This is a preview of subscription content, log in via an institution.
Recommended Reading
Atici A, Servedio RA (2008) Learning unions of ω(1)-dimensional rectangles. Theoretical Computer Science 405(3):209 – 222
Blum A, Furst M, Kearns M, Lipton R (1994) Cryptographic primitives based on hard learning problems. In: Stinson D (ed) Advances in cryptology—CRYPTO ’93. Lecture notes in computer science, vol 773, pp 278–291. Springer, Berlin/Heidelberg
Bshouty NH, Feldman V (2002) On using extended statistical queries to avoid membership queries. J Mach Learn Res 2:359–395
Bshouty NH, Jackson JC (1999) Learning DNF over the uniform distribution using a quantum example oracle. SIAM J Comput 28(3):1136–1153
Bshouty NH, Jackson JC, Tamon C (2004) More efficient PAC-learning of DNF with membership queries under the uniform distribution. J Comput Syst Sci 68(1):205–234
Bshouty NH, Mossel E, O’Donnell R, Servedio RA (2005) Learning DNF from random walks. J Comput Syst Sci 71(3):250–265
Feldman V (2007) Attribute-efficient and non-adaptive learning of parities and DNF expressions. J Mach Learn Res 8:1431–1460
Feldman V (2010) Distribution-specific agnostic boosting. In: Proceedings of innovations in computer science, Tsinghua University, Beijing, pp 241–250
Feldman V (2012) Learning DNF expressions from Fourier spectrum. In: COLT 2012—the 25th annual conference on learning theory, Edinburgh, pp 17.1–17.19
Freund Y (1995) Boosting a weak learning algorithm by majority. Inf Comput 121(2):256–285
Goldreich O, Levin LA (1989) A hard-core predicate for all one-way functions. In: Proceedings of the twenty first annual ACM symposium on theory of computing, Seattle, pp 25–32
Gopalan P, Kalai AT, Klivans AR (2008) Agnostically learning decision trees. In: Proceedings of the 40th annual ACM symposium on theory of computing, STOC ’08, Victoria, pp 527–536. ACM, New York
Jackson J (1997) An efficient membership-query algorithm for learning DNF with respect to the uniform distribution. J Comput Syst Sci 55(3):414–440
Jackson J, Shamir E, Shwartzman C (1999) Learning with queries corrupted by classification noise. Discret Appl Math 92(2–3):157–175
Jackson JC, Wimmer K (2009) New results for random walk learning. In: Dasgupta S, Klivans A (eds) Proceedings of the 22nd annual conference on learning theory, Montreal, pp 267–276. Omnipress, Madison
Jackson JC, Klivans AR, Servedio RA (2002) Learnability beyond A C 0. In: STOC ’02: Proceedings of the thiry-fourth annual ACM symposium on theory of computing, Montréal, pp 776–784. ACM, New York
Kalai AT, Samorodnitsky A, Teng SH (2009) Learning and smoothed analysis. In: Proceedings of the 50th IEEE symposium on foundations of computer science (FOCS), Atlanta, pp 395–404
Kalai AT, Kanade V, Mansour Y (2012) Reliable agnostic learning. J Comput Syst Sci 78(5):1481–1495. {JCSS} Special Issue: Cloud Computing 2011
Kearns MJ, Vazirani UV (1994) An introduction to computational learning theory. MIT, Cambridge
Kearns MJ, Schapire RE, Sellie LM (1994) Toward efficient agnostic learning. Mach Learn 17(2–3):115–141
Klivans AR, Servedio RA (2003) Boosting and hard-core set construction. Mach Learn 51(3):217–238
Kushilevitz E, Mansour Y (1993) Learning decision trees using the Fourier spectrum. SIAM J Comput 22(6):1331–1348
Sellie L (2009) Exact learning of random DNF over the uniform distribution. In: Proceedings of the 41st annual ACM symposium on theory of computing, STOC ’09, Bethesda, pp 45–54. ACM, New York
Valiant LG (1984) A theory of the learnable. Commun ACM 27(11):1134–1142
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer Science+Business Media New York
About this entry
Cite this entry
Jackson, J.C. (2014). Learning DNF Formulas. In: Kao, MY. (eds) Encyclopedia of Algorithms. Springer, Boston, MA. https://doi.org/10.1007/978-3-642-27848-8_196-2
Download citation
DOI: https://doi.org/10.1007/978-3-642-27848-8_196-2
Received:
Accepted:
Published:
Publisher Name: Springer, Boston, MA
Online ISBN: 978-3-642-27848-8
eBook Packages: Springer Reference Computer SciencesReference Module Computer Science and Engineering