Sciweavers

2711 search results - page 317 / 543
» Convergence of the Wake-Sleep Algorithm
Sort
View
AUTOMATICA
2008
82views more  AUTOMATICA 2008»
15 years 4 months ago
Iterative minimization of H2 control performance criteria
Data-based control design methods most often consist of iterative adjustment of the controller's parameters towards the parameter values which minimize an H2 performance crit...
Alexandre S. Bazanella, Michel Gevers, Ljubisa Mis...
CORR
2010
Springer
165views Education» more  CORR 2010»
15 years 4 months ago
Online Learning: Beyond Regret
We study online learnability of a wide class of problems, extending the results of [26] to general notions of performance measure well beyond external regret. Our framework simult...
Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari
SIAMJO
2010
83views more  SIAMJO 2010»
15 years 2 months ago
The Lifted Newton Method and Its Application in Optimization
Abstract. We present a new “lifting” approach for the solution of nonlinear optimization problems (NLPs) that have objective and constraint functions with intermediate variable...
Jan Albersmeyer, Moritz Diehl
ICAI
2010
15 years 2 months ago
Exact Loopy Belief Propagation on Euler Graphs
Belief propagation is widely used in inference of graphical models. It yields exact solutions when the underlying graph is singly connected. When the graph contains loops, double-c...
Chen-Hsiang Yeang
SIAMIS
2010
141views more  SIAMIS 2010»
14 years 11 months ago
Optimization by Stochastic Continuation
Simulated annealing (SA) and deterministic continuation are well-known generic approaches to global optimization. Deterministic continuation is computationally attractive but produ...
Marc C. Robini, Isabelle E. Magnin