Skip to content

v0.3.4 kl weight
Compare
Choose a tag to compare
@kmdalton kmdalton released this 14 Jul 01:42
· 94 commits to main since this release
v0.3.4
f2d3a35
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.

This version adds a new feature to the CLI, the --kl-weight parameter. When --kl-weight is specified, the log likelihood and kl divergence terms in the loss function are reduced by taking the mean rather than the sum. The ELBO is then computed as

ELBO = mean(log_likelihood) + kl_weight * mean(kl_div)

This feature will be useful in making comparisons across isomorphous data sets of different sizes.

Assets 2
Loading