Sciweavers

1506 search results - page 56 / 302
» On the Distribution of Natural Probability Functions
Sort
View
CORR
2010
Springer
158views Education» more  CORR 2010»
13 years 4 months ago
Counting in Graph Covers: A Combinatorial Characterization of the Bethe Entropy Function
We present a combinatorial characterization of the Bethe entropy function of a factor graph, such a characterization being in contrast to the original, analytical, definition of th...
Pascal O. Vontobel
CORR
2008
Springer
118views Education» more  CORR 2008»
13 years 7 months ago
Learning Low-Density Separators
Abstract. We define a novel, basic, unsupervised learning problem learning the the lowest density homogeneous hyperplane separator of an unknown probability distribution. This task...
Shai Ben-David, Tyler Lu, Dávid Pál,...
PODC
2006
ACM
14 years 1 months ago
Computing separable functions via gossip
Motivated by applications to sensor, peer-to-peer, and adhoc networks, we study the problem of computing functions of values at the nodes in a network in a totally distributed man...
Damon Mosk-Aoyama, Devavrat Shah
SIGMOD
2007
ACM
125views Database» more  SIGMOD 2007»
14 years 7 months ago
Optimizing mpf queries: decision support and probabilistic inference
Managing uncertain data using probabilistic frameworks has attracted much interest lately in the database literature, and a central computational challenge is probabilistic infere...
Héctor Corrada Bravo, Raghu Ramakrishnan
TIT
1998
70views more  TIT 1998»
13 years 7 months ago
The Importance of Convexity in Learning with Squared Loss
We show that if the closureof a function class F under the metric induced by some probability distribution is not convex, then the sample complexity for agnostically learning F wi...
Wee Sun Lee, Peter L. Bartlett, Robert C. Williams...