Sciweavers

7 search results - page 1 / 2
» A generalized discrepancy and quadrature error bound
Sort
View
MOC
1998
65views more  MOC 1998»
13 years 4 months ago
A generalized discrepancy and quadrature error bound
An error bound for multidimensional quadrature is derived that includes the Koksma-Hlawka inequality as a special case. This error bound takes the form of a product of two terms. O...
Fred J. Hickernell
MOC
2002
118views more  MOC 2002»
13 years 4 months ago
The error bounds and tractability of quasi-Monte Carlo algorithms in infinite dimension
Dimensionally unbounded problems are frequently encountered in practice, such as in simulations of stochastic processes, in particle and light transport problems and in the problem...
Fred J. Hickernell, Xiaoqun Wang
MOC
2002
92views more  MOC 2002»
13 years 4 months ago
Asymptotic properties of the spectral test, diaphony, and related quantities
This paper presents the limit laws of discrepancies defined via exponential sums, and algorithms (with error bounds) to approximate the corresponding distribution functions. The re...
Hannes Leeb
TNN
2010
143views Management» more  TNN 2010»
12 years 11 months ago
Using unsupervised analysis to constrain generalization bounds for support vector classifiers
Abstract--A crucial issue in designing learning machines is to select the correct model parameters. When the number of available samples is small, theoretical sample-based generali...
Sergio Decherchi, Sandro Ridella, Rodolfo Zunino, ...
ML
2002
ACM
141views Machine Learning» more  ML 2002»
13 years 4 months ago
On the Existence of Linear Weak Learners and Applications to Boosting
We consider the existence of a linear weak learner for boosting algorithms. A weak learner for binary classification problems is required to achieve a weighted empirical error on t...
Shie Mannor, Ron Meir