Sciweavers

574 search results - page 42 / 115
» Approximation Algorithms for Free-Label Maximization
Sort
View
CCR
2006
122views more  CCR 2006»
13 years 8 months ago
Low complexity, stable scheduling algorithms for networks of input queued switches with no or very low speed-up
The delay and throughput characteristics of a packet switch depend mainly on the queueing scheme and the scheduling algorithm deployed at the switch. Early research on scheduling ...
Claus Bauer
JMLR
2010
129views more  JMLR 2010»
13 years 3 months ago
Expectation Truncation and the Benefits of Preselection In Training Generative Models
We show how a preselection of hidden variables can be used to efficiently train generative models with binary hidden variables. The approach is based on Expectation Maximization (...
Jörg Lücke, Julian Eggert
DAGM
2006
Springer
14 years 10 days ago
Provably Correct Edgel Linking and Subpixel Boundary Reconstruction
Existing methods for segmentation by edgel linking are based on heuristics and give no guarantee for a topologically correct result. In this paper, we propose an edgel linking algo...
Ullrich Köthe, Peer Stelldinger, Hans Meine
ML
2008
ACM
13 years 8 months ago
Large margin vs. large volume in transductive learning
Abstract. We consider a large volume principle for transductive learning that prioritizes the transductive equivalence classes according to the volume they occupy in hypothesis spa...
Ran El-Yaniv, Dmitry Pechyony, Vladimir Vapnik
SIGMOD
2001
ACM
160views Database» more  SIGMOD 2001»
14 years 8 months ago
Adaptive Precision Setting for Cached Approximate Values
Caching approximate values instead of exact values presents an opportunity for performance gains in exchange for decreased precision. To maximize the performance improvement, cach...
Chris Olston, Boon Thau Loo, Jennifer Widom