Decoupled PFNs: Identifiable Epistemic-Aleatoric Decomposition via Structured Synthetic Priors
arXiv:2605.06413v1 Announce Type: new
Abstract: Prior-Fitted Networks (PFNs) amortize Bayesian prediction by meta-learning over a synthetic task prior, but their standard output is a posterior predictive distribution over noisy observations. For seque…