Public Member Functions | List of all members
ldaplusplus::em::MultinomialSupervisedEStep< Scalar > Class Template Reference
Inheritance diagram for ldaplusplus::em::MultinomialSupervisedEStep< Scalar >:
ldaplusplus::em::AbstractEStep< Scalar > ldaplusplus::em::EStepInterface< Scalar > ldaplusplus::events::EventDispatcherComposition

Public Member Functions

 MultinomialSupervisedEStep (size_t e_step_iterations=10, Scalar e_step_tolerance=1e-2, Scalar mu=2, Scalar eta_weight=1, Scalar compute_likelihood=1.0, int random_state=0)
std::shared_ptr< parameters::Parametersdoc_e_step (const std::shared_ptr< corpus::Document > doc, const std::shared_ptr< parameters::Parameters > parameters) override
- Public Member Functions inherited from ldaplusplus::em::AbstractEStep< Scalar >
 AbstractEStep (int random_state)
virtual void e_step () override
- Public Member Functions inherited from ldaplusplus::events::EventDispatcherComposition
std::shared_ptr< EventDispatcherInterfaceget_event_dispatcher ()
void set_event_dispatcher (std::shared_ptr< EventDispatcherInterface > dispatcher)

Additional Inherited Members

- Protected Member Functions inherited from ldaplusplus::em::AbstractEStep< Scalar >
bool converged (const Eigen::Matrix< Scalar, Eigen::Dynamic, 1 > &gamma_old, const Eigen::Matrix< Scalar, Eigen::Dynamic, 1 > &gamma, Scalar tolerance)
PRNGget_prng ()

Constructor & Destructor Documentation

template<typename Scalar >
ldaplusplus::em::MultinomialSupervisedEStep< Scalar >::MultinomialSupervisedEStep ( size_t  e_step_iterations = 10,
Scalar  e_step_tolerance = 1e-2,
Scalar  mu = 2,
Scalar  eta_weight = 1,
Scalar  compute_likelihood = 1.0,
int  random_state = 0 
e_step_iterationsThe max number of times to alternate between maximizing for \(\gamma\) and for \(\phi\).
e_step_toleranceThe minimum relative change in the variational parameter \(\gamma\).
muThe uniform Dirichlet prior of \(\eta\), practically is a smoothing parameter during the maximization of \(\eta\).
eta_weightA weighting parameter that either increases or decreases the influence of the supervised part.
compute_likelihoodThe percentage of documents to compute likelihood for (1.0 means compute for every document)
random_stateAn initial seed value for any random numbers needed

Member Function Documentation

template<typename Scalar >
std::shared_ptr< parameters::Parameters > ldaplusplus::em::MultinomialSupervisedEStep< Scalar >::doc_e_step ( const std::shared_ptr< corpus::Document doc,
const std::shared_ptr< parameters::Parameters parameters 

Maximize the ELBO w.r.t. \(\phi\) and \(\gamma\).

The following steps are the mathematics that are implemented where \(\beta\) are the over words topics distributions, \(\alpha\) is the Dirichlet prior, \(\eta\) are the logistic regression parameters, \(i\) is the topic subscript, \(n\) is the word subscript, \(\hat{y}\) is the class subscript, \(y\) is the document's class, \(w_n\) is n-th word vocabulary index, \(m \) is a weighting parameter used to adjust the influence of the supervised part and finally \(\Psi(\cdot)\) is the first derivative of the \(\log \Gamma\) function.

  1. Repeat until convergence of \(\gamma\).
  2. Compute \(\phi_{ni} \propto \beta_{iw_n}\eta_{yi}^m\exp\left( \Psi(\gamma_i)\right)\)
  3. Compute \(\gamma_i = \alpha_i + \sum_n^N \phi_{ni} \)
docA single document.
parametersAn instance of class Parameters, which contains all necessary model parameters for e-step's implementation.
The variational parameters for the current model, after e-step is completed.

Implements ldaplusplus::em::EStepInterface< Scalar >.

The documentation for this class was generated from the following files: