B. Apolloni, C. Gentile  Home/Search
Context
Related
| laren.usr.dsi.unimi.it/en...Vers3.ps.gz Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: laren.usr.dsi.unimi.it...articles (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: Working in the framework of PAC-learning theory, we present special statistics for accomplishing in polynomial time proper learning of DNF boolean formulas having a fixed number of monomials. Our statistics turn out to be near sufficient for a large family of distribution laws---that we call butterfly distributions. We develop a theory of most powerful learning for analyzing the performance of learning algorithms, with particular reference to trade-offs between power and computational costs.... (Update)
Active bibliography (related documents): More All
0.3: Learning from Incomplete Boundary Queries Using Split.. - Sloan, Turán (1997) (Correct)
0.3: Local Search for Satisfiability (SAT) Problem - Gu (1993) (Correct)
0.2: A Complete and Tight Average-Case Analysis of Learning.. - Reischuk, Zeugmann (1998) (Correct)
Similar documents based on text: More All
0.3: Journal of Machine Learning Research 2 (2001) 213-242.. - Cation Algorithm Claudio (Correct)
0.3: From Synapses to Rules - Apolloni, Malchiodi, Orovas, Palmas (2001) (Correct)
0.3: Narrowing confidence interval width of PAC learning risk.. - Apolloni, Malchiodi (Correct)
BibTeX entry: (Update)
@article{ apolloni00psufficient,
author = "B. Apolloni and Claudio Gentile",
title = "P-Sufficient Statistics for {PAC} Learning k-term-{DNF} Formulas through Enumeration",
journal = "Theoretical Computer Science",
volume = "230",
number = "1-2",
pages = "1-37",
year = "2000",
url = "citeseer.ist.psu.edu/209086.html" }
Citations (may not include all citations):572 Computer and Intractability (context) - GAREY, JOHNSON - 1979
493 Communication of ACM (context) - of, learnable - 1984
465 Learnability and the VapnikChervonenkis dimension (context) - BLUMER, EHRENFEUCHT et al. - 1989
454 the uniform convergence of relative frequencies of events to.. (context) - VAPNIK, CHERVONENKIS - 1971
348 Estimation of dependences based on empirical data (context) - VAPNIK - 1982
245 A measure of asymptotic efficiency for tests of a hypothesis.. (context) - CHERNOFF - 1952
215 Learning decision-lists - RIVEST - 1987
169 A formal theory of inductive inference (context) - SOLOMONOFF - 1964
151 A general lower bound on the number of examples needed for l.. (context) - EHRENFEUCHT, HAUSSLER et al. - 1988
144 Computational limitations on learning from examples (context) - PITT, VALIANT - 1988
142 Learning from noisy examples (context) - ANGLUIN, LAIRD - 1988
115 the density of families of sets (context) - On - 1972
107 Efficient Noise-Tolerant Learning From Statistical Queries - KEARNS - 1993
94 Learning in the presence of malicious errors - KEARNS, LI - 1988
84 Learning disjunctions of conjunctions (context) - VALIANT - 1985
78 the learnability of boolean formulae - KEARNS, LI et al. - 1987
75 Mathematical Statistics (context) - WILKS - 1962
66 Structural Complexity (context) - BALCAZAR, DIAZ et al. - 1988
66 Constant depth circuits (context) - LINIAL, MANSOUR et al. - 1989
48 Classifying learnable geometric concepts with the Vapnik-Che.. (context) - BLUMER, EHRENFEUCHT et al. - 1986
43 Wiley-Teubner Series in Computer Science (context) - Complexity, Functions - 1987
42 term-DNF formulas with queries (context) - BLUM, RUDICH - 1992
37 Statistical Queries and faulty PAC Oracles - DECATUR - 1993
27 University of California Press (context) - of - 1950
27 term-DNF formulas using queries and counterexamples (context) - k- - 1987
22 DNF formulas on product distributions (context) - HANCOCK, MANSOUR - 1991
20 An introduction to Probability Theory and Mathematical Stati.. (context) - ROHATGI - 1976
18 Learning DNF under the uniform distribution in quasi-polynom.. (context) - VERBEURGT - 1990
8 Proper learning algorithm for functions of k-terms under smo.. (context) - SAKAY, TAKIMOTO et al. - 1995
7 Learning Monotone Log-term DNF formulas (context) - SAKAI, MARUOKA - 1994
7 Investigating the distribution assumptions in the PAC learni.. (context) - BARTLETT, WILLIAMSON - 1991
4 PAC Learning of concept classes through the boundaries of th.. - APOLLONI, CHIARAVALLI - 1997
3 Learning monotone Boolean functions by uniformly distributed.. (context) - GU, MARUOKA - 1992
1 of the 3th Workshop on Algorithmic Learning Theory (context) - SAKAI, MARUOKA - 1992
1 Learning DNF formulas under Classes of Probability Distribut.. (context) - FLAMMINI, MARCHETTI-SPACCAMELA et al. - 1992
1 Noisy oracles for learning k-term DNF formulas (context) - GENTILE, MAURI - 1994
1 and unbiased estimation (context) - LEHMANN, SCHEFFE - 1950
1 of the 5th Workshop on Comput (context) - BENEDEK, ITAI - 1992
1 rd Workshop on Comput (context) - BLUM, SINGH et al. - 1990
Documents on the same site (http://laren.usr.dsi.unimi.it/en/articles.html): More
Sample Size Lower Bounds in PAC Learning by Algorithmic.. - Apolloni, Gentile (1998) (Correct)
A Hybrid Symbolic Subsymbolic Controller for Complex.. - Apolloni, Piccolboni.. (Correct)
Correlation Collapse under Persistent Input Derangement .. - Apolloni, de Falco.. (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC