Sciweavers

227 search results - page 18 / 46
» A PAC Bound for Approximate Support Vector Machines
Sort
View
PODS
2009
ACM
100views Database» more  PODS 2009»
14 years 8 months ago
Space-optimal heavy hitters with strong error bounds
The problem of finding heavy hitters and approximating the frequencies of items is at the heart of many problems in data stream analysis. It has been observed that several propose...
Radu Berinde, Graham Cormode, Piotr Indyk, Martin ...
CIARP
2010
Springer
13 years 4 months ago
A New Algorithm for Training SVMs Using Approximate Minimal Enclosing Balls
Abstract. It has been shown that many kernel methods can be equivalently formulated as minimal-enclosing-ball (MEB) problems in certain feature space. Exploiting this reduction eff...
Emanuele Frandi, Maria Grazia Gasparo, Stefano Lod...
COLT
2001
Springer
13 years 12 months ago
Rademacher and Gaussian Complexities: Risk Bounds and Structural Results
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 ...
Peter L. Bartlett, Shahar Mendelson
IJCNN
2007
IEEE
14 years 1 months ago
Upper Bound on Pattern Storage in Feedforward Networks
—Starting from the strict interpolation equations for multivariate polynomials, an upper bound is developed for the number of patterns that can be memorized by a nonlinear feedfo...
Pramod Lakshmi Narasimha, Michael T. Manry, Franci...
JMLR
2010
159views more  JMLR 2010»
13 years 2 months ago
Semi-Supervised Learning with Max-Margin Graph Cuts
This paper proposes a novel algorithm for semisupervised learning. This algorithm learns graph cuts that maximize the margin with respect to the labels induced by the harmonic fun...
Branislav Kveton, Michal Valko, Ali Rahimi, Ling H...