Sciweavers

568 search results - page 52 / 114
» New bounds for the Cebysev functional
Sort
View
ICML
2003
IEEE
14 years 8 months ago
Using Linear-threshold Algorithms to Combine Multi-class Sub-experts
We present a new type of multi-class learning algorithm called a linear-max algorithm. Linearmax algorithms learn with a special type of attribute called a sub-expert. A sub-exper...
Chris Mesterharm
WEA
2010
Springer
241views Algorithms» more  WEA 2010»
14 years 2 months ago
A Branch-and-Price Algorithm for Multi-mode Resource Leveling
Resource leveling is a variant of resource-constrained project scheduling in which a non-regular objective function, the resource availability cost, is to be minimized. We present ...
Eamonn T. Coughlan, Marco E. Lübbecke, Jens S...
ESA
2009
Springer
130views Algorithms» more  ESA 2009»
14 years 2 months ago
On the Performance of Approximate Equilibria in Congestion Games
We study the performance of approximate Nash equilibria for congestion games with polynomial latency functions. We consider how much the price of anarchy worsens and how much the ...
George Christodoulou, Elias Koutsoupias, Paul G. S...
ML
2007
ACM
131views Machine Learning» more  ML 2007»
13 years 7 months ago
A primal-dual perspective of online learning algorithms
We describe a novel framework for the design and analysis of online learning algorithms based on the notion of duality in constrained optimization. We cast a sub-family of universa...
Shai Shalev-Shwartz, Yoram Singer
ICPR
2010
IEEE
13 years 6 months ago
Incremental Training of Multiclass Support Vector Machines
We present a new method for the incremental training of multiclass Support Vector Machines that provides computational efficiency for training problems in the case where the trai...
Symeon Nikitidis, Nikos Nikolaidis, Ioannis Pitas