Sciweavers

267 search results - page 34 / 54
» Distribution arithmetic for stochastical analysis
Sort
View
ICANN
2010
Springer
13 years 9 months ago
Empirical Analysis of the Divergence of Gibbs Sampling Based Learning Algorithms for Restricted Boltzmann Machines
Abstract. Learning algorithms relying on Gibbs sampling based stochastic approximations of the log-likelihood gradient have become a common way to train Restricted Boltzmann Machin...
Asja Fischer, Christian Igel
JSS
2010
142views more  JSS 2010»
13 years 3 months ago
Analysis of service availability for time-triggered rejuvenation policies
In this paper we investigate the effect of three time-triggered system rejuvenation policies on service availability using a queuing model. The model is formulated as an extended ...
Felix Salfner, Katinka Wolter
EOR
2007
85views more  EOR 2007»
13 years 8 months ago
Modeling and analysis of a supply-assembly-store chain
We consider a supply–assembly–store chain with produce-to-stock strategy, which comprises a set of component suppliers, a mixed-model assembly line with a constantly moving co...
Xiaobo Zhao, Deju Xu, Hanqin Zhang, Qi-Ming He
INFOCOM
2005
IEEE
14 years 2 months ago
Gossip algorithms: design, analysis and applications
Abstract— Motivated by applications to sensor, peer-topeer and ad hoc networks, we study distributed asynchronous algorithms, also known as gossip algorithms, for computation and...
Stephen P. Boyd, Arpita Ghosh, Balaji Prabhakar, D...
STOC
2004
ACM
150views Algorithms» more  STOC 2004»
14 years 9 months ago
Typical properties of winners and losers in discrete optimization
We present a probabilistic analysis for a large class of combinatorial optimization problems containing, e.g., all binary optimization problems defined by linear constraints and a...
René Beier, Berthold Vöcking