Sciweavers

33 search results - page 4 / 7
» Semigroup Kernels on Finite Sets
Sort
View
JMLR
2002
137views more  JMLR 2002»
13 years 5 months ago
The Subspace Information Criterion for Infinite Dimensional Hypothesis Spaces
A central problem in learning is selection of an appropriate model. This is typically done by estimating the unknown generalization errors of a set of models to be selected from a...
Masashi Sugiyama, Klaus-Robert Müller
TCS
2008
13 years 5 months ago
Kernel methods for learning languages
This paper studies a novel paradigm for learning formal languages from positive and negative examples which consists of mapping strings to an appropriate highdimensional feature s...
Leonid Kontorovich, Corinna Cortes, Mehryar Mohri
ICIP
2006
IEEE
14 years 7 months ago
Tomographic Approach for Sampling Multidimensional Signals with Finite Rate of Innovation
Recently, it was shown that it is possible to sample classes of 1D and 2-D signals with finite rate of innovation (FRI) [9, 4, 5, 3, 2, 7]. In particular, in [7], we presented loc...
Pancham Shukla, Pier Luigi Dragotti
SODA
2010
ACM
261views Algorithms» more  SODA 2010»
14 years 3 months ago
Bidimensionality and Kernels
Bidimensionality theory appears to be a powerful framework in the development of meta-algorithmic techniques. It was introduced by Demaine et al. [J. ACM 2005 ] as a tool to obtai...
Fedor V. Fomin, Daniel Lokshtanov, Saket Saurabh, ...
CORR
2010
Springer
140views Education» more  CORR 2010»
13 years 6 months ago
Performance Bounds and Design Criteria for Estimating Finite Rate of Innovation Signals
In this paper, we consider the problem of estimating finite rate of innovation (FRI) signals from noisy measurements, and specifically analyze the interaction between FRI technique...
Zvika Ben-Haim, Tomer Michaeli, Yonina C. Eldar