(Enter summary)
Abstract: We are interested in distributions which are derived
as a maximumentropy distribution given
a set of constraints. More specifically, we are
interested in the case where the constraints are
the expectation of individual and pairs of attributes.
For such a given maximum entropy
distribution we develop an efficient learning algorithm
for read-once DNF. We also show how
to extend our results to monotone read-k DNF,
following the techniques of [HM91]
1 Introduction
The PAC learning model [Val84] is ... (Update)
Cited by: More
Decision Trees: More Theoretical Justification for Practical.. - Fiat, Pechyony
(Correct)
Decision Trees: More Theoretical Justification for Practical.. - Pechyony (2004)
(Correct)
Decision Trees: More Theoretical Justification - For Practical Algorithms
(Correct)
Active bibliography (related documents): More All
0.2: Reasoning by Evidence for Best-Chance Planning with Incomplete.. - Lozinskii
(Correct)
0.2: Wavelets and Digital Image Processing - Maaß, Stark (1994)
(Correct)
0.2: Regularization Tools - A Matlab Package for Analysis and Solution .. - Hansen (1998)
(Correct)
Similar documents based on text: More All
0.4: Weakly Learning DNF and Characterizing Statistical .. - Blum, Furst.. (1994)
(Correct)
0.3: Simple Learning Algorithms for Decision Trees and.. - Bshouty, Mansour (1995)
(Correct)
0.2: An O(n^(log log n)) Learning Algorithm for DNF under the Uniform.. - Mansour (1998)
(Correct)
Related documents from co-citation: More All
4: Quantifying inductive bias: AI learning algorithms and Valiant's learning framew.. (context) - Haussler - 1988
4: Weakly learning DNF and characterizing statistical query learning using Fourier ..
- Blum, Furst et al. - 1994
4: for approximating set cover (context) - Feige, of - 1996
BibTeX entry: (Update)
Y. Mansour and M. Schain. Learning with Maximum-Entropy Distributions. Machine Learning, 45(2):123-145, 2001. http://citeseer.ist.psu.edu/mansour01learning.html More
@inproceedings{ mansour97learning,
author = "Yishay Mansour and Mariano Schain",
title = "Learning with Maximum-Entropy Distributions",
booktitle = "Computational Learing Theory",
pages = "201-210",
year = "1997",
url = "citeseer.ist.psu.edu/mansour01learning.html" }
Citations (may not include all citations):
2319
Elements of Information Theory (context) - Cover, Thomas - 1991
537
A theory of the learnable (context) - Valiant
471
and Stochastic Processes (context) - Papoulis, Random - 1991
144
Computational limitations on learning from examples (context) - Pitt, Valiant - 1988
107
Efficient noise-tolerant learning from statistical queries
- Kearns - 1993
82
When won't membership queries help (context) - Angluin, Kharitonov - 1991
81
Equivalence of models for polynomial learnability (context) - Haussler, Kearns et al. - 1990
34
Learnability by fixed distributions (context) - Benedek, Itai - 1988
29
Constructing small sample spaces satisfying given constraint..
- Koller, Megiddo - 1993
25
On learning boolean functions (context) - Natarajan - 1987
22
DNF Formulas on Product Distributions (context) - Hancock, Mansour - 1991
15
Learning boolean formulas (context) - Kearns, Li et al. - 1994
12
Learning boolean formulae or finite automata is as hard as f.. (context) - Kearns, Valiant - 1988
5
the complexity of statistical reasoning
- Kilian, Naor - 1995
4
Maximum-Entropy and Bayesian Methods in Inverse Problems (context) - Ray, Jr et al. - 1985
Documents on the same site (http://www.math.tau.ac.il/~mansour/cv.htm): More
Randomized Interpolation and Approximation of Sparse Polynomials - Mansour (1995)
(Correct)
Efficient Algorithms for Learning to Play Repeated .. - Freund, Kearns.. (1996)
(Correct)
On Construction of k-wise Independent Random Variables - Karloff, Mansour (1994)
(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