Sciweavers

2711 search results - page 102 / 543
» Convergence of the Wake-Sleep Algorithm
Sort
View
TIT
2008
76views more  TIT 2008»
15 years 3 months ago
Improved Risk Tail Bounds for On-Line Algorithms
We prove the strongest known bound for the risk of hypotheses selected from the ensemble generated by running a learning algorithm incrementally on the training data. Our result i...
Nicolò Cesa-Bianchi, Claudio Gentile
CONEXT
2009
ACM
15 years 4 months ago
Improving internet-wide routing protocols convergence with MRPC timers
The behavior of routing protocols during convergence is critical as it impacts end-to-end performance. Network convergence is particularly important in BGP, the current interdomai...
Anthony J. Lambert, Marc-Olivier Buob, Steve Uhlig
EOR
2008
106views more  EOR 2008»
15 years 3 months ago
Convergent Lagrangian heuristics for nonlinear minimum cost network flows
We consider the separable nonlinear and strictly convex single-commodity network flow problem (SSCNFP). We develop a computational scheme for generating a primal feasible solution...
Torbjörn Larsson, Johan Marklund, Caroline Ol...
CVPR
2009
IEEE
16 years 11 months ago
On Compositional Image Alignment with an Application to Active Appearance Models
Efficient and accurate fitting of Active Appearance Models (AAM) is a key requirement for many applications. The most efficient fitting algorithm today is Inverse Compositional ...
Brian Amberg (University of Basel), Andrew Blake (...
ICML
2007
IEEE
16 years 4 months ago
On learning linear ranking functions for beam search
Beam search is used to maintain tractability in large search spaces at the expense of completeness and optimality. We study supervised learning of linear ranking functions for con...
Yuehua Xu, Alan Fern