Sciweavers

3415 search results - page 109 / 683
» Lower Bounds for Kernelizations
Sort
View
97
Voted
NECO
2010
97views more  NECO 2010»
14 years 11 months ago
Rademacher Chaos Complexities for Learning the Kernel Problem
In this paper we develop a novel generalization bound for learning the kernel problem. First, we show that the generalization analysis of the kernel learning problem reduces to in...
Yiming Ying, Colin Campbell
JMLR
2010
132views more  JMLR 2010»
14 years 8 months ago
On the Impact of Kernel Approximation on Learning Accuracy
Kernel approximation is commonly used to scale kernel-based algorithms to applications containing as many as several million instances. This paper analyzes the effect of such appr...
Corinna Cortes, Mehryar Mohri, Ameet Talwalkar
132
Voted
ALGORITHMICA
2008
111views more  ALGORITHMICA 2008»
15 years 1 months ago
Fixed-Parameter Complexity of Minimum Profile Problems
The profile of a graph is an integer-valued parameter defined via vertex orderings; it is known that the profile of a graph equals the smallest number of edges of an interval supe...
Gregory Gutin, Stefan Szeider, Anders Yeo
150
Voted
STOC
2010
ACM
224views Algorithms» more  STOC 2010»
15 years 5 months ago
Satisfiability Allows No Nontrivial Sparsification Unless The Polynomial-Time Hierarchy Collapses
Consider the following two-player communication process to decide a language L: The first player holds the entire input x but is polynomially bounded; the second player is computa...
Holger Dell and Dieter van Melkebeek
117
Voted
EACL
2006
ACL Anthology
15 years 2 months ago
Making Tree Kernels Practical for Natural Language Learning
In recent years tree kernels have been proposed for the automatic learning of natural language applications. Unfortunately, they show (a) an inherent super linear complexity and (...
Alessandro Moschitti