Sciweavers

143 search results - page 8 / 29
» Subgradient methods and consensus algorithms for solving con...
Sort
View
NIPS
2008
13 years 8 months ago
On the Generalization Ability of Online Strongly Convex Programming Algorithms
This paper examines the generalization properties of online convex programming algorithms when the loss function is Lipschitz and strongly convex. Our main result is a sharp bound...
Sham M. Kakade, Ambuj Tewari
JMLR
2010
169views more  JMLR 2010»
13 years 2 months ago
Consensus-Based Distributed Support Vector Machines
This paper develops algorithms to train support vector machines when training data are distributed across different nodes, and their communication to a centralized processing unit...
Pedro A. Forero, Alfonso Cano, Georgios B. Giannak...
JSAC
2007
109views more  JSAC 2007»
13 years 7 months ago
Optimization of Semi-Dynamic Lightpath Rearrangements in a WDM Network
— In this paper, we study the Routing and Wavelength Assignment (RWA) problem in a semi-dynamic scenario where rearrangements are conducted in a series of sessions after traffic...
Yiming Zhang, Oliver W. W. Yang, Jing Wu, Michel S...
ICASSP
2009
IEEE
14 years 2 months ago
A wavelet-based quadratic extension method for image deconvolution in the presence of poisson noise
Iterative optimization algorithms such as the forward-backward and Douglas-Rachford algorithms have recently gained much popularity since they provide efficient solutions to a wi...
Nelly Pustelnik, Caroline Chaux, Jean-Christophe P...
ICML
2004
IEEE
14 years 8 months ago
Multiple kernel learning, conic duality, and the SMO algorithm
While classical kernel-based classifiers are based on a single kernel, in practice it is often desirable to base classifiers on combinations of multiple kernels. Lanckriet et al. ...
Francis R. Bach, Gert R. G. Lanckriet, Michael I. ...