Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

11

ICML
2002
IEEE

favoriteEmaildiscussreport

146views Machine Learning» more ICML 2002»

On generalization bounds, projection profile, and margin distribution

14 years 5 months ago

Download valis.cs.uiuc.edu

We study generalization properties of linear learning algorithms and develop a data dependent approach that is used to derive generalization bounds that depend on the margin distribution. Our method makes use of random projection techniques to allow the use of existing VC dimension bounds in the effective, lower, dimension of the data. Comparisons with existing generalization bound show that our bounds are tighter and meaningful in cases existing bounds are not.

Ashutosh Garg, Sariel Har-Peled, Dan Roth

Real-time Traffic

Cases Existing Bounds | Generalization Bounds | ICML 2002 | Machine Learning | VC Dimension Bounds |

claim paper

Related Content

» On the generalization of soft margin algorithms

» Margin Distribution and Learning

» Maximum Relative Margin and DataDependent Regularization

» Generalization error bounds in semisupervised classification under the cluster assumption

» On the Margin Explanation of Boosting Algorithms

» Totally corrective boosting algorithms that maximize the margin

» On the Generalization Ability of OnLine Learning Algorithms

» Boosting Algorithms for Maximizing the Soft Margin

» MaxMargin MinEntropy Models

Post Info
More Details (n/a)

Added	17 Nov 2009
Updated	17 Nov 2009
Type	Conference
Year	2002
Where	ICML
Authors	Ashutosh Garg, Sariel Har-Peled, Dan Roth

Comments (0)