MoMPrior-class

MoM-class

MoMPrior

An S4 class to represent a Mixture of Multinomial model.
Such model can be used to cluster a data matrix $X$ with the following generative model :
$$ \pi \sim Dirichlet(\alpha)$$
$$ Z_i \sim \mathcal{M}(1,\pi)$$
$$ \theta_{k} \sim Dirichlet(\beta)$$
$$ X_{i.}|Z_{ik}=1 \sim \mathcal{M}(L_i,\theta_{k})$$
With $L_i=\sum_d=1^DX_{id}$. These classes mainly store the prior parameters value ($\alpha,\beta$) of this generative model.
The <code>MoM-class</code> must be used when fitting a simple Mixture of Multinomials whereas the <code>MoMPrior-class</code> must be sued when fitting a <code>CombinedModels-class</code>.

An ensemble of algorithms that enable the clustering of networks and data matrices (such as counts, categorical or continuous) with different type of generative models. Model selection and clustering is performed in combination by optimizing the Integrated Classification Likelihood (which is equivalent to minimizing the description length). Several models are available such as: Stochastic Block Model, degree corrected Stochastic Block Model, Mixtures of Multinomial, Latent Block Model. The optimization is performed thanks to a combination of greedy local search and a genetic algorithm (see <arXiv:2002:11577> for more details).

Etienne C<c3><b4>me

greed

Clustering and Model Selection with the Integrated
Classification Likelihood

Etienne Côme

Nicolas Jouvin

MoM function

<dl><dt>beta</dt>
<dd>Dirichlet over vocabulary prior parameter (default to 1)</dd>
<dt>alpha</dt>
<dd>Dirichlet prior parameter over the cluster proportions (default to 1)</dd></dl>

Arguments

Mixture of Multinomial Model Prior description class — MoM

<dl>

<dt>beta</dt>
<dd>Dirichlet over vocabulary prior parameter (default to 1)</dd>


<dt>alpha</dt>
<dd>Dirichlet prior parameter over the cluster proportions (default to 1)</dd>

</dl>

MoM: Mixture of Multinomial Model Prior description class

Description

Usage

Value

Arguments

See Also

Examples