See this document in CiteSeerX!

Learning from Data of Variable Quality  (Make Corrections)  
Koby Crammer, Michael Kearns, Jennifer Wortman Computer and Information...



  Home/Search   Context   Related

 
View or download:
books.nips.cc/pape...IPS2005_0427.ps.gz
Cached:  PS.gz  PS  PDF   Image  Update  Help

From:  books.nips.cc/nips18 (more)
(Enter author homepages)

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

Abstract: We initiate the study of learning from multiple sources of limited data, each of which may be corrupted at a different rate. We develop a complete theory of which data sources should be used for two fundamental problems: estimating the bias of a coin, and learning a classifier in the presence of label noise. In both cases, efficient algorithms are provided for computing the optimal subset of data. (Update)

Active bibliography (related documents):   More   All
0.0:   On the Stochastic Complexity of Learning Realizable and.. - Meir, Merhav (1995)   (Correct)
0.0:   Algorithmic Stability and Sanity-Check Bounds for Leave-One-Out .. - Kearns, Ron (1997)   (Correct)
0.0:   Distribution-Dependent Vapnik-Chervonenkis Bounds - Vayatis, Azencott (1999)   (Correct)

Similar documents based on text:
0.0:   Unknown -   (Correct)

BibTeX entry:   (Update)

@misc{ michael-learning,
  author = "Koby Crammer Michael",
  title = "Learning from Data of Variable Quality",
  url = "citeseer.ist.psu.edu/757704.html" }
Citations (may not include all citations):
947   Statistical Learning Theory (context) - Vapnik - 1998
248   An Introduction to Computational Learning Theory (context) - Kearns, Vazirani - 1994
180   Combining labeled and unlabeled data with co-training - Blum, Mitchell - 1998
102   Towards efficient agnostic learning - Kearns, Schapire et al. - 1994
47   Rigorous learning curve bounds from statistical mechanics - Haussler, Kearns et al. - 1994

Documents on the same site (http://books.nips.cc/nips18.html):   More
Q-Clustering - Narasimhan, Jojic, Bilmes (2005)   (Correct)
Statistical Convergence of Kernel CCA - Kenji Fukumizu Institute   (Correct)
Large-Scale Biophysical Parameter Estimation in - Single Neurons Via   (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