Faithful inversion of generative models for effective amortized inference
Inference amortization methods share information across multiple posteriorinference problems, allowing each to be carried out more efficiently. Generally, they require the inversion of the dependency structure in the generative model, as the modeller must learn a mapping from observations to distrib...
Hauptverfasser: | Webb, S, Golinski, A, Zinkov, R, Narayanaswamy, S, Rainforth, T, Teh, Y, Wood, F |
---|---|
Format: | Conference item |
Veröffentlicht: |
Curran Associates
2019
|
Ähnliche Einträge
Ähnliche Einträge
-
Amortized Monte Carlo integration
von: Goliński, A, et al.
Veröffentlicht: (2019) -
Amortized rejection sampling in universal probabilistic programming
von: Naderiparizi, S, et al.
Veröffentlicht: (2022) -
Amortized inference and model learning for probabilistic programming
von: Le, TA
Veröffentlicht: (2019) -
Kilonova Spectral Inverse Modelling with Simulation-based Inference: An Amortized Neural Posterior Estimation Analysis
von: P. Darc, et al.
Veröffentlicht: (2024-01-01) -
Target–aware Bayesian inference: how to beat optimal conventional estimators
von: Rainforth, T, et al.
Veröffentlicht: (2020)