Author name cluster

Dmitry Rusakov

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

JMLR Journal 2005 Journal Article

Asymptotic Model Selection for Naive Bayesian Networks

Dmitry Rusakov
Dan Geiger

We develop a closed form asymptotic formula to compute the marginal likelihood of data given a naive Bayesian network model with two hidden states and binary features. This formula deviates from the standard BIC score. Our work provides a concrete example that the BIC score is generally incorrect for statistical models that belong to stratified exponential families. This claim stands in contrast to linear and curved exponential families, where the BIC score has been proven to provide a correct asymptotic approximation for the marginal likelihood. [abs] [ pdf ][ bib ] &copy JMLR 2005. ( edit, beta )

PDF Details

UAI Conference 2003 Conference Paper

Automated Analytic Asymptotic Evaluation of the Marginal Likelihood for Latent Models

Dmitry Rusakov
Dan Geiger

We present and implement two algorithms for analytic asymptotic evaluation of the marginal likelihood of data given a Bayesian network with hidden nodes. As shown by previous work, this evaluation is particularly hard for latent Bayesian network models, namely networks that include hidden variables, where asymptotic approximation deviates from the standard BIC score. Our algorithms solve two central difficulties in asymptotic evaluation of marginal likelihood integrals, namely, evaluation of regular dimensionality drop for latent Bayesian network models and computation of non-standard approximation formulas for singular statistics for these models. The presented algorithms are implemented in Matlab and Maple and their usage is demonstrated for marginal likelihood approximations for Bayesian networks with hidden variables

Details

UAI Conference 2002 Conference Paper

Asymptotic Model Selection for Naive Bayesian Networks

Dmitry Rusakov
Dan Geiger

We develop a closed form asymptotic formula to compute the marginal likelihood of data given a naive Bayesian network model with two hidden states and binary features. This formula deviates from the standard BIC score. Our work provides a concrete example that the BIC score is generally not valid for statistical models that belong to a stratified exponential family. This stands in contrast to linear and curved exponential families, where the BIC score has been proven to provide a correct approximation for the marginal likelihood.

Details

AAAI Conference 1999 Conference Paper

Selective Sampling for Nearest Neighbor Classifiers

Michael Lindenbaum
Shaul Markovich
Dmitry Rusakov
Technion - Israel Institute of Technology

In the passive, traditional, approachto learning, the information available to the learner is a set of classified examples, whichare randomlydrawnfrom the instance space. In many applications, however, the initial classification of the training set is a costly process, andan intelligently selection of training examplesfromunlabeled data is doneby an active learner. This paper proposesa loolmheadalgorithm for example selection and addresses the problemof active learning in the context of nearest neighborclassifiers. Theproposedapproachrelies on using a random field modelfor the examplelabeling, whichimplies a dynamicchange of the label estimates during the samplingprocess. The proposedselective samplingalgorithm wasevaluated empirically on artificial andreal data sets. The experiments showthat the proposed method outperforms other methodsin most cases.

PDF Details