Self-Supervised Laplace Approximation for Bayesian Uncertainty Quantification

ArXi:2605.12208v1 Announce Type: cross Approximate Bayesian inference typically revolves around computing the posterior parameter distribution. In practice, however, the main object of interest is often a model's predictions rather than its parameters. In this work, we propose to bypass the parameter posterior and focus directly on approximating the posterior predictive distribution. We achieve this by drawing inspiration from self-