Sciweavers

2520 search results - page 231 / 504
» The complexity of approximating entropy
Sort
View
NIPS
2008
15 years 8 months ago
Continuously-adaptive discretization for message-passing algorithms
Continuously-Adaptive Discretization for Message-Passing (CAD-MP) is a new message-passing algorithm for approximate inference. Most message-passing algorithms approximate continu...
Michael Isard, John MacCormick, Kannan Achan
SODA
2004
ACM
87views Algorithms» more  SODA 2004»
15 years 8 months ago
Optimal space lower bounds for all frequency moments
We prove that any one-pass streaming algorithm which ( , )-approximates the kth frequency moment Fk, for any real k = 1 and any = 1 m , must use 1 2 bits of space, where m is th...
David P. Woodruff
NIPS
1994
15 years 7 months ago
Efficient Methods for Dealing with Missing Data in Supervised Learning
We present efficient algorithms for dealing with the problem of missing inputs (incomplete feature vectors) during training and recall. Our approach is based on the approximation ...
Volker Tresp, Ralph Neuneier, Subutai Ahmad
UAI
1996
15 years 7 months ago
Asymptotic Model Selection for Directed Networks with Hidden Variables
We extend the Bayesian Information Criterion (BIC), an asymptotic approximation for the marginal likelihood, to Bayesian networks with hidden variables. This approximation can be ...
Dan Geiger, David Heckerman, Christopher Meek
CORR
2010
Springer
113views Education» more  CORR 2010»
15 years 6 months ago
Traffic Capacity of Large WDM Passive Optical Networks
As passive optical networks (PON) are increasingly deployed to provide high speed Internet access, it is important to understand their fundamental traffic capacity limits. The pape...
Nelson Antunes, Christine Fricker, Philippe Robert...