Sciweavers

1331 search results - page 194 / 267
» Complexity bounds for zero-test algorithms
Sort
View
ICML
2010
IEEE
14 years 11 months ago
Multi-Class Pegasos on a Budget
When equipped with kernel functions, online learning algorithms are susceptible to the "curse of kernelization" that causes unbounded growth in the model size. To addres...
Zhuang Wang, Koby Crammer, Slobodan Vucetic
ICML
2008
IEEE
15 years 10 months ago
An RKHS for multi-view learning and manifold co-regularization
Inspired by co-training, many multi-view semi-supervised kernel methods implement the following idea: find a function in each of multiple Reproducing Kernel Hilbert Spaces (RKHSs)...
Vikas Sindhwani, David S. Rosenberg
CVPR
2007
IEEE
15 years 12 months ago
Solving Large Scale Binary Quadratic Problems: Spectral Methods vs. Semidefinite Programming
In this paper we introduce two new methods for solving binary quadratic problems. While spectral relaxation methods have been the workhorse subroutine for a wide variety of comput...
Carl Olsson, Anders P. Eriksson, Fredrik Kahl
CVPR
2008
IEEE
15 years 12 months ago
Approximate earth mover's distance in linear time
The earth mover's distance (EMD) [16] is an important perceptually meaningful metric for comparing histograms, but it suffers from high (O(N3 log N)) computational complexity...
Sameer Shirdhonkar, David W. Jacobs
ICML
1996
IEEE
15 years 10 months ago
On the Learnability of the Uncomputable
Within Valiant'smodel of learning as formalized by Kearns, we show that computable total predicates for two formallyuncomputable problems the classical Halting Problem, and t...
Richard H. Lathrop