AI RESEARCH
Occam's Razor is Only as Sharp as Your ELBO
arXiv CS.LG
•
ArXi:2604.25984v1 Announce Type: cross The marginal likelihood, also known as the evidence, is regarded as a mathematical embodiment of Occam's razor, enabling model selection that avoids overfitting. The evidence lower bound (ELBO) objective from variational inference has also been used for similar purposes. Prior work has shown that restricting the approximate posterior family via a mean-field approximation can lead the ELBO to underfit.