Attribute-efficient learning and weight-degree tradeoffs for polynomial threshold functions

Journal of Machine Learning Research

Volumn 23, Issue , 2012, Pages

  Servedio, Rocco A ^a   Tan, Li Yang ^a   Thaler, Justin ^b  

^a Fu Foundation School of Engineering and Applied Science   (United States)

^b HARVARD UNIVERSITY   (United States)

Author keywords

Attribute efficient learning; Decision lists; Markov's inequality; Polynomial threshold functions

Indexed keywords

ARTIFICIAL INTELLIGENCE; SOFTWARE ENGINEERING;

ATTRIBUTE-EFFICIENT LEARNING; BOOLEAN VARIABLES; DECISION LISTS; LOWER BOUNDS; MARKOV'S INEQUALITY; MISTAKE BOUNDS; POLYNOMIAL THRESHOLD FUNCTIONS; RUNNING TIME;

POLYNOMIALS;

EID: 84893271540     PISSN: 15324435     EISSN: 15337928     Source Type: Journal    
DOI: None     Document Type: Conference Paper

References (19)

1. Richard Beigel. Perceptrons, PP, and the Polynomial Hierarchy. Computational Complexity, 4: 339-349, 1994.
2. Avrim Blum. Learning boolean functions in an infinite atribute space (extended abstract). In STOC, pages 64-72. ACM, 1990.
3. Avrim Blum and Pat Langley. Selection of relevant features and examples in machine learning. Artif. Intell., 97(1-2):245-271, 1997.
4. Avrim Blum, Lisa Hellerstein, and Nick Littlestone. Learning in the presence of finitely or infinitely many irrelevant attributes. J. Comput. Syst. Sci., 50(1):32-40, 1995.
5. Peter Borwein and Taḿas Erd́elyi. Markov-Bernstein type inequalities under Littlewood-type coefficient constraints. Indagationes Mathematicae, 11(2):159 - 172, 2000. ISSN 0019-3577. doi: 10.1016/S0019-3577(00) 89074-6.
6. Harry Buhrman, Nikolai K. Vereshchagin, and Ronald de Wolf. On computation and communication with small bias. In IEEE Conference on Computational Complexity, pages 24-32. IEEE Computer Society, 2007.
7. Adam R. Klivans and Rocco A. Servedio. Toward attribute efficient learning of decision lists and parities. Journal of Machine Learning Research, 7:587-602, 2006.
8. Adam R. Klivans and Alexander A. Sherstov. Lower bounds for agnostic learning via approximate rank. Computational Complexity, 19(4):581-604, 2010.
9. Matthias Krause and Pavel Pudĺak. On computing boolean functions by sparse real polynomials. In FOCS, pages 682-691. IEEE Computer Society, 1995.
10. Matthias Krause and Pavel Pudĺak. Computing boolean functions by polynomials and threshold circuits. Computational Complexity, 7(4):346-370, 1998.
11. N. Littlestone. From online to batch learning. In Proceedings of the Second Annual Workshop on Computational Learning Theory, pages 269-284, 1989.
12. Nick Littlestone. Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm. Machine Learning, 2(4):285-318, 1987.
13. P. Long and R. Servedio. Attribute-efficient learning of decision lists and linear threshold functions under unconcentrated distributions. In Proc. 20th Annual Conference on Neural Information Processing Systems (NIPS), 2006.
14. Ziv Nevo and Ran El-Yaniv. On online learning of decision lists. Journal of Machine Learning Research, 3:271-301, 2002.
15. Noam Nisan and Mario Szegedy. On the degree of boolean functions as real polynomials. Computational Complexity, 4:301-313, 1994.
16. Alexander A. Sherstov. Halfspace matrices. Computational Complexity, 17(2):149-178, 2008.
17. Alexander A. Sherstov. Separating ac0 from depth-2 majority circuits. SIAM J. Comput., 38(6): 2113-2129, 2009.
18. Alexander A. Sherstov. The pattern matrix method. SIAM J. Comput., 40(6):1969-2000, 2011.
19. Leslie G. Valiant. Projection learning. Machine Learning, 37(2):115-130, 1999.