Sciweavers

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

14

JMLR
2010

favoriteEmaildiscussreport

143views more JMLR 2010»

Rademacher Complexities and Bounding the Excess Risk in Active Learning

12 years 11 months ago

Rademacher Complexities and Bounding the Excess Risk in Active Learning

Download fodava.gatech.edu

Sequential algorithms of active learning based on the estimation of the level sets of the empirical risk are discussed in the paper. Localized Rademacher complexities are used in the algorithms to estimate the sample sizes needed to achieve the required accuracy of learning in an adaptive way. Probabilistic bounds on the number of active examples have been proved and several applications to binary classification problems are considered.

Vladimir Koltchinskii

Real-time Traffic

Binary Classification Problems | JMLR 2010 | Rademacher Complexities | Sequential Algorithms |

claim paper

Related Content

» Rademacher and Gaussian Complexities Risk Bounds and Structural Results

» Rademacher Chaos Complexities for Learning the Kernel Problem

» On the Complexity of Linear Prediction Risk Bounds Margin Bounds and Regularization

» Sample compression bounds for decision trees

» A Unifying View of Multiple Kernel Learning

» Bayesian Active Learning Using Arbitrary Binary Valued Queries

» On the Interaction between Norm and Dimensionality Multiple Regimes in Learning

» Radial Basis Function Networks and Complexity Regularization in Function Learning

» Forest Density Estimation

Post Info
More Details (n/a)

Added	19 May 2011
Updated	19 May 2011
Type	Journal
Year	2010
Where	JMLR
Authors	Vladimir Koltchinskii

Comments (0)