Almanac
technique

Prior-Data Fitted Networks

techniqueactiveprovisionalprior-data-fitted-networks-a456f7de·1 events·first seen 47h ago

Aliases: Prior-Data Fitted Networks

Co-occurring entities

More like this (12)

Recent events (1)

5arXiv · cs.LG·47h ago·source ↗

Multi-Task Bayesian In-Context Learning for Amortized Hierarchical Inference

A new arXiv preprint introduces a multi-task in-context learning framework for amortized hierarchical Bayesian predictive inference, representing prior information as a prefix of in-context datasets fed to a transformer. The model learns to adapt predictions across families of priors, addressing the brittleness of prior-data fitted models under distribution shift. On evaluations including out-of-meta-distribution priors and high-dimensional latent structures, the method matches oracle Bayesian predictors while being orders of magnitude faster, with a real-world spatiotemporal temperature prediction demonstration.