Description Usage Arguments Value
The *un-normalised* prior over W in SpStPCA. This is a product of the StPCA Gaussian prior and an iid Laplace prior. p(W | \beta, b) = \prod^k_i=1 N(w_i | 0, K) * \prod^d_i=1 \prod^k_j=1 Laplace(W_ij | 0, b)
1 | log_sparse_prior_W(K, W, b)
|
K |
Prior covariance matrix |
W |
Loadings matrix |
b |
Variance on Laplace part of prior |
un-normalised log prior over W
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.