Sciweavers

614 search results - page 34 / 123
» Globally Convergent Autocalibration
Sort
View
NIPS
2007
15 years 1 months ago
Bundle Methods for Machine Learning
We present a globally convergent method for regularized risk minimization problems. Our method applies to Support Vector estimation, regression, Gaussian Processes, and any other ...
Alex J. Smola, S. V. N. Vishwanathan, Quoc V. Le
FOCM
2007
94views more  FOCM 2007»
14 years 11 months ago
Trust-Region Methods on Riemannian Manifolds
A general scheme for trust-region methods on Riemannian manifolds is proposed and analyzed. Among the various approaches available to (approximately) solve the trust-region subpro...
Pierre-Antoine Absil, C. G. Baker, Kyle A. Galliva...
SIAMJO
2008
141views more  SIAMJO 2008»
14 years 11 months ago
Constraint Nondegeneracy, Strong Regularity, and Nonsingularity in Semidefinite Programming
It is known that the Karush-Kuhn-Tucker (KKT) conditions of semidefinite programming can be reformulated as a nonsmooth system via the metric projector over the cone of symmetric ...
Zi Xian Chan, Defeng Sun
SODA
2008
ACM
93views Algorithms» more  SODA 2008»
15 years 1 months ago
Fast load balancing via bounded best response
It is known that the dynamics of best response in an environment of non-cooperative users may converge to a good solution when users play sequentially, but may cycle far away from...
Baruch Awerbuch, Yossi Azar, Rohit Khandekar
FLAIRS
2003
15 years 1 months ago
Sample Complexity of Real-Coded Evolutionary Algorithms
Researchers studying Evolutionary Algorithms and their applications have always been confronted with the sample complexity problem. The relationship between population size and gl...
Jian Zhang 0007, Xiaohui Yuan, Bill P. Buckles