Author

Lukas Sablica

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Jun 2025

Spherical Cauchy Variational Autoencoders: Heavy Angular Tails and Exact KL Evaluation

The spherical Cauchy distribution is developed as a hyperspherical posterior that needs neither compromise and has broader angular tails and a smaller KL penalty than both alternatives, so equal local precision costs less regularization.

Lukas Sablica, Kurt Hornik · 3 citations