lasso_deltas

Generate initial Markov chain state with Lasso.

internal

Efficient Bayesian multinomial logistic regression based on heavy-tailed
(hyper-LASSO, non-convex) priors. The posterior of coefficients and hyper-parameters
is sampled with restricted Gibbs sampling for leveraging the high-dimensionality and
Hamiltonian Monte Carlo for handling the high-correlation among coefficients. A detailed
description of the method: Li and Yao (2018),
Journal of Statistical Computation and Simulation, 88:14, 2827-2851, <doi:10.48550/arXiv.1405.3319>.

Steven Liu

HTLR

Bayesian Logistic Regression with Heavy-Tailed Priors

Longhai Li

lasso_deltas function

<dl><dt>X</dt>
<dd>Design matrix of traning data; 
rows should be for the cases, and columns for different features.</dd>
<dt>y</dt>
<dd>Vector of class labels in training or test data set. 
Must be coded as non-negative integers, e.g., 1,2,...,C for C classes.</dd>
<dt>lambda</dt>
<dd>A user supplied lambda sequence for <code>glmnet</code> cross-validation.
<code>NULL</code> by default, and it will be generated by <code>glmnet</code>.</dd>
<dt>alpha</dt>
<dd>The elasticnet mixing parameter for <code>glmnet</code>.</dd></dl>

Arguments

Lasso Initial State — lasso_deltas

<dl>

<dt>X</dt>
<dd>Design matrix of traning data; 
rows should be for the cases, and columns for different features.</dd>


<dt>y</dt>
<dd>Vector of class labels in training or test data set. 
Must be coded as non-negative integers, e.g., 1,2,...,C for C classes.</dd>


<dt>lambda</dt>
<dd>A user supplied lambda sequence for <code>glmnet</code> cross-validation.
<code>NULL</code> by default, and it will be generated by <code>glmnet</code>.</dd>


<dt>alpha</dt>
<dd>The elasticnet mixing parameter for <code>glmnet</code>.</dd>

</dl>

lasso_deltas: Lasso Initial State

Description

Usage

Value

Arguments

References

See Also