Persistant “PCD vs CD” topic

PCD is assumed to converge to the real distribution of the model as it samples from last particle states at each learning iteration. However, the model is constantly changing from an iteration to another, so how can we affirm that PCD is closer than CD to model distribution before the model get stable?

Advertisements

0 Responses to “Persistant “PCD vs CD” topic”



  1. Leave a Comment

Leave a Reply

Please log in using one of these methods to post your comment:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

w

Connecting to %s





%d bloggers like this: