Table 1: 
Preliminary experiments reporting the mean±stdev. of the KL divergence (in nats) between the proposed posterior approximation (Eq. 5) and: (i) the left-to-right LM, (ii) the right-to-left LM, and (iii) a simple product of experts baseline (Eq. 5, but with the uniform distribution for q(w)).
ModelKL Div. with Posterior Approx.
Left-to-right LM 2.27±1.84 
Right-to-left LM 2.04±1.87 
Product of Experts 1.12±1.08 
ModelKL Div. with Posterior Approx.
Left-to-right LM 2.27±1.84 
Right-to-left LM 2.04±1.87 
Product of Experts 1.12±1.08 
View Large
Close Modal
This Feature Is Available To Subscribers Only

or Create an Account

Close Modal
Close Modal
This site uses cookies. By continuing to use our website, you are agreeing to our privacy policy. No content on this site may be used to train artificial intelligence systems without permission in writing from the MIT Press.
Accept