ICON is shown to compute the posterior predictive mean of differential equation solutions, and a generative extension, GenICON, provides samples from this distribution for uncertainty quantification.
An explanation of in-context learning as implicit Bayesian inference
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
support 1representative citing papers
citing papers explorer
-
Probabilistic operator learning: generative modeling and uncertainty quantification for foundation models of differential equations
ICON is shown to compute the posterior predictive mean of differential equation solutions, and a generative extension, GenICON, provides samples from this distribution for uncertainty quantification.