Risk Bounds and Structural Results Peter L. Bartlett...  Home/Search
Context
Related
| jmlr.org/papers/volum...bartlett02a.pdf 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: berkeley.edu/~bartlett/...pubs93 (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: We investigate the use of certain data-dependent estimates of the complexity of a function class, called Rademacher and Gaussian complexities. In a decision theoretic setting, we prove general risk bounds in terms of these complexities. We consider function classes that can be expressed as combinations of functions from basis classes and show how the Rademacher and Gaussian complexities of such a function class can be bounded in terms of the complexity of the basis classes. We give... (Update)
Similar documents (at the sentence level):
27.3%: Journal of Machine Learning Research 3 (2002) 463-482.. - Risk Bounds And (Correct)
27.3%: Rademacher and Gaussian Complexities: Risk Bounds and.. - Bartlett, Mendelson (2002) (Correct)
Active bibliography (related documents): More All
0.4: Convexity, Classification, and Risk Bounds - Peter Bartlett Bartlett (Correct)
0.3: Analysis of Data with Threshold Decision Lists - Martin Anthony December (Correct)
0.3: Error Bounds for Voting Classifiers Using Margin Cost.. - Mason, Bartlett, Baxter (1999) (Correct)
Similar documents based on text:
0.0: Unknown - (Correct)
BibTeX entry: (Update)
@misc{ and-journal,
author = "Risk Bounds And",
title = "Journal of Machine Learning Research 3 (2002) 463-482 Submitted 11/01;
Published 11/02 Rademacher and Gaussian Complexities:",
url = "citeseer.ist.psu.edu/756407.html" }
Citations (may not include all citations):454 the uniform convergence of relative frequencies of events to.. (context) - Vapnik, Chervonenkis - 1971
91 The sample complexity of pattern classification with neural .. - Bartlett - 1998
88 Neural Network Learning: Theoretical Foundations (context) - Anthony, Bartlett - 1999
78 Boosting the margin: a new explanation for the e#ectiveness .. (context) - Schapire, Freund et al. - 1998
66 An experimental and theoretical comparison of model selectio.. - Kearns, Mansour et al. - 1997
56 The volume of convex bodies and Banach space geometry (context) - Pisier - 1989
43 Improved generalization through explicit optimization of mar.. - Mason, Bartlett et al. - 2000
33 the method of bounded di#erences (context) - McDiarmid - 1989
31 Rademacher and gaussian complexities: Risk bounds and struct.. - Bartlett, Mendelson - 2001
24 Model selection and error estimation - Bartlett, Boucheron et al. - 2002
17 Rademacher penalties and structural risk minimization - Koltchinskii - 2001
17 Using output codes to boost multiclass learning problems - Schapire - 1997
16 Probability in Banach Spaces: isoperimetry and processes (context) - Ledoux, Talagrand - 1991
12 Applications of Mathematics: Stochastic Modelling and Applie.. (context) - Devroye, Gyorfi et al. - 1996
7 Rademacher averages and phase transitions in Glivenko-Cantel.. - Mendelson - 2002
7 Generalization in decision trees and DNF: Does size matter - Golea, Bartlett et al. - 1998
5 Banach-Mazur distance and finite-dimensional operator ideals (context) - Tomczak-Jaegermann - 1989
4 norm and its application to learning theory - Mendelson - 2001
3 An Introduction to Support Vector Methods (context) - Cristianini, Shawe-Taylor - 2000
3 Structural risk minimisation over data-dependent hierarchies (context) - Shawe-Taylor, Bartlett et al. - 1998
Documents on the same site (http://www.stat.berkeley.edu/~bartlett/publications/pubs-93.html): More
Large Margin Classifiers: Convex Loss, Low Noise, and.. - Bartlett, Jordan.. (Correct)
Faster Convergence Rates for Error Probabilities of - Message Passing Decoders (Correct)
Convexity, Classification, and Risk Bounds - Peter Bartlett Bartlett (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