Zobrazeno 1 - 10
of 97
pro vyhledávání: '"Højsgaard, Søren"'
The capability of R to do symbolic mathematics is enhanced by the caracas package. This package uses the Python computer algebra library SymPy as a back-end but caracas is tightly integrated in the R environment. This enables the R user with symbolic
Externí odkaz:
http://arxiv.org/abs/2301.13777
We propose Unity Smoothing (US) for handling inconsistencies between a Bayesian network model and new unseen observations. We show that prediction accuracy, using the junction tree algorithm with US is comparable to that of Laplace smoothing. Moreove
Externí odkaz:
http://arxiv.org/abs/2201.08659
Autor:
Højsgaard, Søren, Lauritzen, Steffen
In Gaussian graphical models, the likelihood equations must typically be solved iteratively. We investigate two algorithms: A version of iterative proportional scaling which avoids inversion of large matrices, and an algorithm based on convex duality
Externí odkaz:
http://arxiv.org/abs/2112.10388
The capability of R to do symbolic mathematics is enhanced by the caracas package. This package uses the Python computer algebra library SymPy as a back-end but caracas is tightly integrated in the R environment, thereby enabling the R user with symb
Externí odkaz:
http://arxiv.org/abs/2104.05292
A graphical model is a multivariate (potentially very high dimensional) probabilistic model, which is formed by combining lower dimensional components. Inference (computation of conditional probabilities) is based on message passing algorithms that u
Externí odkaz:
http://arxiv.org/abs/2103.03647
Autor:
Andersen, Mikkel Meyer1 mikl@math.aau.dk, Højsgaard, Søren1 sorenh@math.aau.dk
Publikováno v:
R Journal. Dec2023, Vol. 15 Issue 4, p181-197. 17p.
Autor:
Hojsgaard, Soren
There are two main objectives of this paper. The first is to present a statistical framework for models with context specific independence structures, i.e., conditional independences holding only for sepcific values of the conditioning variables. Thi
Externí odkaz:
http://arxiv.org/abs/1301.3863
Autor:
O'Connell, Jared, Tøgersen, Frede Aakmann, Friggens, Nicolas C., Løvendahl, Peter, Højsgaard, Søren
Publikováno v:
Journal of Agricultural, Biological, and Environmental Statistics, 2011 Mar 01. 16(1), 1-16.
Externí odkaz:
https://www.jstor.org/stable/23208305
Publikováno v:
Journal of the Royal Statistical Society. Series B (Statistical Methodology), 2008 Nov 01. 70(5), 1005-1027.
Externí odkaz:
https://www.jstor.org/stable/20203867