Sciweavers

356 search results - page 11 / 72
» Submodular Approximation: Sampling-based Algorithms and Lowe...
Sort
View
UAI
2004
13 years 9 months ago
PAC-learning Bounded Tree-width Graphical Models
We show that the class of strongly connected graphical models with treewidth at most k can be properly efficiently PAC-learnt with respect to the Kullback-Leibler Divergence. Prev...
Mukund Narasimhan, Jeff A. Bilmes
EMMCVPR
2011
Springer
12 years 7 months ago
Branch and Bound Strategies for Non-maximal Suppression in Object Detection
In this work, we are concerned with the detection of multiple objects in an image. We demonstrate that typically applied objectives have the structure of a random field model, but...
Matthew B. Blaschko
IPMU
2010
Springer
13 years 11 months ago
Credal Sets Approximation by Lower Probabilities: Application to Credal Networks
Abstract. Credal sets are closed convex sets of probability mass functions. The lower probabilities specified by a credal set for each element of the power set can be used as cons...
Alessandro Antonucci, Fabio Cuzzolin
FOCS
2008
IEEE
14 years 2 months ago
Linear Level Lasserre Lower Bounds for Certain k-CSPs
We show that for k ≥ 3 even the Ω(n) level of the Lasserre hierarchy cannot disprove a random k-CSP instance over any predicate type implied by k-XOR constraints, for example ...
Grant Schoenebeck
SIGMOD
2002
ACM
127views Database» more  SIGMOD 2002»
14 years 8 months ago
Approximate XML joins
XML is widely recognized as the data interchange standard for tomorrow, because of its ability to represent data from a wide variety of sources. Hence, XML is likely to be the for...
Sudipto Guha, H. V. Jagadish, Nick Koudas, Divesh ...