Koji Tsuda, Gunnar Rätsch, Sebastian Mika, Klaus-Robert Müller  Home/Search
Context
Related
| anu.edu.au/~raetsc...aeMikMue00_meta.ps 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: anu.edu.au/~raetsch/ps/ (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: We propose a meta learning framework, casting leave-one-out (LOO) error approximation into a classification problem. For Support Vector Machines this means that we need to learn a classification of whether or not a given Support Vector -- if left out of the data set -- would be misclassified. For this learning task, simple data set dependent features are proposed, inspired by bounds from learning theory and geometrical intuition. Our approach allows to predict the LOO error on unseen... (Update)
Similar documents (at the sentence level):
8.9%: Learning to Predict the Leave-one-out Error of Kernel.. - Tsuda, Rätsch, Mika.. (Correct)
Active bibliography (related documents): More All
0.2: A Tutorial on ν-Support Vector Machines - Chen, Lin, Schölkopf (Correct)
0.2: A PAC-Bayesian Margin Bound for Linear Classifiers - Herbrich, Graepel (2002) (Correct)
0.2: Combining Discriminant Models with new Multi-Class SVMs - Guermeur (2000) (Correct)
Similar documents based on text: More All
2.1: Learning to Predict the Leave-one-out Error - Tsuda, Rätsch, Mika, Müller (2000) (Correct)
0.6: Two Efficient Methods for Computing Leave-One-Out Error in.. - Keerthi, Ong, Lee (2000) (Correct)
0.6: A Mathematical Programming Approach to the Kernel Fisher.. - Mika, Rätsch, Müller (2001) (Correct)
BibTeX entry: (Update)
@misc{ tsuda-meta,
author = "Koji Tsuda and Gunnar Rätsch and Sebastian Mika and Klaus-Robert Müller",
title = "Meta Learning: Learning to Predict the Leave-one-out Error",
url = "citeseer.ist.psu.edu/528333.html" }
Citations (may not include all citations):1291 The nature of statistical learning theory (context) - Vapnik - 1995
243 Boosting the margin: a new explanation for the effectiveness.. - Schapire, Freund et al. - 1997
85 Network information criterion---determining the number of hi.. - Murata, Yoshizawa et al. - 1994
75 The evidence framework applied to classification networks - MacKay - 1992
49 New support vector algorithms - Scholkopf, Smola et al. - 2000
39 Probabilistic kernel regression models - Jaakkola, Haussler - 1999
15 Bounds on error expectation for support vector machines - Vapnik, Chapelle - 2000
14 On estimation characters obtained in statistical procedure o.. (context) - Luntz, Brailowsky - 1969
13 Robust ensemble learning (context) - Ratsch, Scholkopf et al. - 1999
12 Generalization bounds via eigenvalues of the Gram matrix - Scholkopf, Shawe-Taylor et al. - 1999
12 Choosing kernel parameters for support vector machines (context) - Chapelle, Vapnik - 2000
8 Gaussian processes and SVM: Mean field and leave-one-out (context) - Opper, Winther - 2000
5 Robust bounds on the generalization from the margin distribu.. (context) - Shawe-Taylor, Cristianini - 1998
3 Generalized approximate cross-validation for support-vectorm.. (context) - Whaba, Lin et al. - 1999
Documents on the same site (http://mlg.anu.edu.au/~raetsch/ps/): More
On the Convergence of Leveraging - Rätsch, Mika, Warmuth (2002) (Correct)
Constructing Boosting Algorithms from SVMs: an.. - Rätsch, Mika.. (2002) (Correct)
Adapting Codes and Embeddings for Polychotomies - Rätsch, Smola, Mika (2003) (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