See this document in CiteSeerX!

General Bounds on Statistical Query Learning and PAC Learning with Noise via Hypothesis Boosting (1993)  (Make Corrections)  (33 citations)
Javed A. Aslam, Scott E. Decatur
Proceedings of the 34rd Annual Symposium on Foundations of Computer Science



  Home/Search   Context   Related

Links:   ACM   DBLP

 
View or download:
mit.edu/~sed/resea...CS93Reprint.ps.gz
Cached:  PS.gz  PS  PDF   Image  Update  Help

From:  jprc.com/Artificial_Intel...index (more)
(Enter author homepages)

Rate this article: (best)
  Comment on this article  
(Enter summary)

Abstract: We derive general bounds on the complexity of learning in the Statistical Query model and in the PAC model with classification noise. We do so by considering the problem of boosting the accuracy of weak learning algorithms which fall within the Statistical Query model. This new model was introduced by Kearns [12] to provide a general framework for efficient PAC learning in the presence of classification noise. We first show a general scheme for boosting the accuracy of weak SQ learning... (Update)

Cited by:   More
Efficient Noise-Tolerant Learning From Statistical Queries - Kearns (1998)   (Correct)
On Using Extended Statistical Queries to Avoid Membership.. - Bshouty, Feldman (2002)   (Correct)
A General Dimension for Query Learning - Jos'e Balc'azar Jorge   (Correct)

Similar documents (at the sentence level):   More
23.3%:   Noise Tolerant Algortihms for Learning and Searching - Aslam (1995)   (Correct)
21.1%:   General Bounds on Statistical Query Learning and PAC Learning .. - Aslam, Decatur (1993)   (Correct)
15.7%:   Noise Tolerant Algorithms for Learning and Searching - Aslam (1995)   (Correct)

Active bibliography (related documents):   More   All
0.2:   Face Recognition Using Boosted Local Features - Jones, Viola (2003)   (Correct)
0.2:   Mitsubishi Electric Research Laboratories - Http Www Merl (2003)   (Correct)
0.2:   Colourful Linear Programming and its Relatives - Bárány, Onn   (Correct)

Similar documents based on text:   More   All
0.9:   .1 Outline - Standard Pac Model   (Correct)
0.3:   The Strength of Weak Learnability - Schapire (1990)   (Correct)
0.3:   Specification and Simulation of Statistical Query Algorithms.. - Javed Aslam (1995)   (Correct)

Related documents from co-citation:   More   All
24:   Efficient noise-tolerant learning from statistical queries - Kearns - 1993
17:   Statistical queries and faulty PAC oracles - Decatur - 1993
16:   The strength of weak learnability - Schapire - 1990

BibTeX entry:   (Update)

J. A. Aslam and S. E. Decatur. General bounds on statistical query learning and PAC learning with noise via hypothesis boosting. In Proceedings of the 34th Annual Symposium on Foundations of Computer Science, pages 282--291, November 1993. http://citeseer.ist.psu.edu/aslam93general.html   More

@inproceedings{ aslam93general,
    author = "Javed A. Aslam and Scott E. Decatur",
    title = "General bounds on statistical query learning and {PAC} learning with noise via hypothesis boosting",
    booktitle = "Proceedings of the 34rd Annual Symposium on Foundations of Computer Science",
    publisher = "IEEE Computer Society Press, Los Alamitos, CA",
    pages = "282--291",
    year = "1993",
    url = "citeseer.ist.psu.edu/aslam93general.html" }
Citations (may not include all citations):
493   Communications of the ACM (context) - Valiant, of et al. - 1984
273   The strength of weak learnability - Schapire - 1990  ACM   DBLP
180   Boosting a weak learning algorithm by majority - Freund - 1990  ACM   DBLP
151   A general lower bound on the number of examples needed for l.. (context) - Ehrenfeucht, Haussler et al. - 1989  ACM   DBLP
142   Learning from noisy examples (context) - Angluin, Laird - 1988  ACM   DBLP
107   Efficient noise-tolerant learning from statistical queries - Kearns - 1993  ACM   DBLP
66   Computational learning theory: Survey and selected bibliogra.. (context) - Angluin - 1992  DBLP
59   Improving performance in neural networks using a boosting al.. (context) - Drucker, Schapire et al. - 1992  ACM   DBLP
52   Learning from Good and Bad Data (context) - Laird - 1988  ACM
45   The Design and Analysis of Efficient Learning Algorithms (context) - Schapire - 1992  ACM
37   An improved boosting algorithm and its implications on learn.. (context) - Freund - 1992  ACM   DBLP
37   Statistical queries and faulty PAC oracles - Decatur - 1993  ACM   DBLP
27   Learning integer lattices (context) - Helmbold, Sloan et al. - 1992  ACM   DBLP
21   Exact identification of circuits using fixed points of ampli.. (context) - Goldman, Kearns et al. - 1990
11   the sample complexity of weak learning (context) - Goldman, Kearns et al. - 1990
9   General bounds on the number of examples needed for learning.. (context) - Simon - 1993  ACM   DBLP
4   Algorithmic Learning of Formal Languages and Decision Trees (context) - Sakakibara - 1991
4   Personal communication (context) - Freund - 1993



The graph only includes citing articles where the year of publication is known.


Documents on the same site (http://www.cora.jprc.com/Artificial_Intelligence/Machine_Learning/Theory/index.html):   More
On the Sample Complexity of Noise-Tolerant Learning - Aslam, Decatur (1996)   (Correct)
Knowing What Doesn't Matter: Exploiting The Omission of.. - Greiner, Grove, Kogan (1994)   (Correct)
Self Bounding Learning Algorithms - Freund (1998)   (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