technique
Prior-Data Fitted Networks
techniqueactiveprovisional
prior-data-fitted-networks-a456f7de·1 events·first seen 47h agoAliases: Prior-Data Fitted Networks
Co-occurring entities
More like this (12)
Pretraining Recurrent Networks without RecurrenceFeedforward Neural NetworksGraph Neural NetworksConservation Laws from Data Symmetry in Neural Networkstemporally ordered pre-trainingAnatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning SignalNNCF (Neural Network Compression Framework)Neural Surrogate ModelsProvenance-Grounded Gating and Adaptive Recovery in Synthetic Post-Training Data CurationUnsupervised Pre-trainingResNetLayer-Adaptive Expert Pruning
Recent events (1)
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.