Sciweavers

337 search results - page 13 / 68
» Semidefinite Programming Based Approximation Algorithms
Sort
View
ICALP
2007
Springer
13 years 11 months ago
Efficient Algorithms for Constant Well Supported Approximate Equilibria in Bimatrix Games
Abstract. In this work we study the tractability of well supported approximate Nash Equilibria (SuppNE in short) in bimatrix games. In view of the apparent intractability of constr...
Spyros C. Kontogiannis, Paul G. Spirakis
ICML
1995
IEEE
14 years 8 months ago
Stable Function Approximation in Dynamic Programming
The success ofreinforcement learninginpractical problems depends on the ability to combine function approximation with temporal di erence methods such as value iteration. Experime...
Geoffrey J. Gordon
ICCAD
2001
IEEE
107views Hardware» more  ICCAD 2001»
14 years 4 months ago
A Convex Programming Approach to Positive Real Rational Approximation
As system integration evolves and tighter design constraints must be met, it becomes necessary to account for the non-ideal behavior of all the elements in a system. Certain devic...
Carlos P. Coelho, Joel R. Phillips, Luis Miguel Si...
JMLR
2008
169views more  JMLR 2008»
13 years 7 months ago
Multi-class Discriminant Kernel Learning via Convex Programming
Regularized kernel discriminant analysis (RKDA) performs linear discriminant analysis in the feature space via the kernel trick. Its performance depends on the selection of kernel...
Jieping Ye, Shuiwang Ji, Jianhui Chen
CORR
2011
Springer
215views Education» more  CORR 2011»
12 years 11 months ago
Lasserre Hierarchy, Higher Eigenvalues, and Approximation Schemes for Quadratic Integer Programming with PSD Objectives
We present an approximation scheme for optimizing certain Quadratic Integer Programming problems with positive semidefinite objective functions and global linear constraints. Thi...
Venkatesan Guruswami, Ali Kemal Sinop