Sciweavers

3049 search results - page 14 / 610
» On the Convergence of Bound Optimization Algorithms
Sort
View
CVPR
2008
IEEE
14 years 9 months ago
Globally optimal bilinear programming for computer vision applications
We present a practical algorithm that provably achieves the global optimum for a class of bilinear programs commonly arising in computer vision applications. Our approach relies o...
Manmohan Krishna Chandraker, David J. Kriegman
CDC
2009
IEEE
211views Control Systems» more  CDC 2009»
14 years 7 days ago
An event-triggered distributed primal-dual algorithm for Network Utility maximization
Abstract— Many problems associated with networked systems can be formulated as network utility maximization (NUM) problems. NUM problems maximize a global separable measure of ne...
Pu Wan, Michael D. Lemmon
ICML
2000
IEEE
14 years 8 months ago
Rates of Convergence for Variable Resolution Schemes in Optimal Control
This paper presents a general method to derive tight rates of convergence for numerical approximations in optimal control when we consider variable resolution grids. We study the ...
Andrew W. Moore, Rémi Munos
EMO
2005
Springer
194views Optimization» more  EMO 2005»
14 years 1 months ago
An EMO Algorithm Using the Hypervolume Measure as Selection Criterion
Abstract. The hypervolume measure is one of the most frequently applied measures for comparing the results of evolutionary multiobjective optimization algorithms (EMOA). The idea t...
Michael Emmerich, Nicola Beume, Boris Naujoks
NIPS
2007
13 years 9 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