[jira] [Created] (MADLIB-1351) Add stopping criteria on perplexity to LDA

["Frank McQuillan (JIRA)" <ji...@apache.org>]

Frank McQuillan created MADLIB-1351:
---------------------------------------

             Summary: Add stopping criteria on perplexity to LDA
                 Key: MADLIB-1351
                 URL: https://issues.apache.org/jira/browse/MADLIB-1351
             Project: Apache MADlib
          Issue Type: New Feature
          Components: Module: Parallel Latent Dirichlet Allocation
            Reporter: Frank McQuillan
             Fix For: v2.0


In LDA 
http://madlib.apache.org/docs/latest/group__grp__lda.html
make stopping criteria on perplexity rather than just number of iterations.

Suggested approach is to do what scikit-learn does
https://scikit-learn.org/stable/modules/generated/sklearn.decomposition.LatentDirichletAllocation.html

evaluate_every : int, optional (default=0)
How often to evaluate perplexity. Only used in fit method. set it to 0 or negative number to not evalute perplexity in training at all. Evaluating perplexity can help you check convergence in training process, but it will also increase total training time. Evaluating perplexity in every iteration might increase training time up to two-fold.

perp_tol : float, optional (default=1e-1)
Perplexity tolerance in batch learning. Only used when evaluate_every is greater than 0.




--
This message was sent by Atlassian JIRA
(v7.6.3#76005)