The Impact of Likelihood Tempering on the Limiting Predictive Moments of Variational Bayesian Linear Neural Networks
arXiv:2610.09132v1 Announce Type: new Abstract: In wide Bayesian neural networks, Gaussian mean-field variational inference is prone to "prior dominance": the Kullback-Leibler (KL) regularization term of the ELBO outweighs the expected log-likelihood, and the variational predictive distribution col…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-08 04:00 · arXiv stat.ML
The Impact of Likelihood Tempering on the Limiting Predictive Moments of Variational Bayesian Linear Neural Networks