Sciweavers

378 search results - page 1 / 76
» New Bounds and Approximations for the Error of Linear Classi...
Sort
View
CIARP
2004
Springer
13 years 10 months ago
New Bounds and Approximations for the Error of Linear Classifiers
In this paper, we derive lower and upper bounds for the probability of error for a linear classifier, where the random vectors representing the underlying classes obey the multivar...
Luís G. Rueda
EWRL
2008
13 years 8 months ago
New Error Bounds for Approximations from Projected Linear Equations
We consider linear fixed point equations and their approximations by projection on a low dimensional subspace. We derive new bounds on the approximation error of the solution, whi...
Huizhen Yu, Dimitri P. Bertsekas
MP
2006
93views more  MP 2006»
13 years 7 months ago
Computation of Error Bounds for P-matrix Linear Complementarity Problems
Abstract We give new error bounds for the linear complementarity problem where the involved matrix is a P-matrix. Computation of rigorous error bounds can be turned into a P-matrix...
Xiaojun Chen, Shuhuang Xiang
TIT
2010
118views Education» more  TIT 2010»
13 years 1 months ago
Joint sampling distribution between actual and estimated classification errors for linear discriminant analysis
Error estimation must be used to find the accuracy of a designed classifier, an issue that is critical in biomarker discovery for disease diagnosis and prognosis in genomics and p...
Amin Zollanvari, Ulisses Braga-Neto, Edward R. Dou...
MP
2010
162views more  MP 2010»
13 years 5 months ago
Approximation accuracy, gradient methods, and error bound for structured convex optimization
Convex optimization problems arising in applications, possibly as approximations of intractable problems, are often structured and large scale. When the data are noisy, it is of i...
Paul Tseng