JANA: Jointly Amortized Neural Approximation of Complex Bayesian Models
Paper i proceeding, 2023

This work proposes “jointly amortized neural approximation” (JANA) of intractable likelihood functions and posterior densities arising in Bayesian surrogate modeling and simulation-based inference. We train three complementary networks in an end-to-end fashion: 1) a summary network to compress individual data points, sets, or time series into informative embedding vectors; 2) a posterior network to learn an amortized approximate posterior; and 3) a likelihood network to learn an amortized approximate likelihood. Their interaction opens a new route to amortized marginal likelihood and posterior predictive estimation - two important ingredients of Bayesian workflows that are often too expensive for standard methods. We benchmark the fidelity of JANA on a variety of simulation models against state-of-the-art Bayesian methods and propose a powerful and interpretable diagnostic for joint calibration. In addition, we investigate the ability of recurrent likelihood networks to emulate complex time series models without resorting to hand-crafted summary statistics.

Författare

Stefan T. Radev

Universität Heidelberg

Marvin Schmitt

Universität Stuttgart

Valentin Pratz

Universität Heidelberg

Umberto Picchini

Chalmers, Matematiska vetenskaper, Tillämpad matematik och statistik

Ullrich Köthe

Universität Heidelberg

Paul Christian Bürkner

Universität Stuttgart

Proceedings of Machine Learning Research

26403498 (eISSN)

Vol. 216 1695-1706

39th Conference on Uncertainty in Artificial Intelligence, UAI 2023
Pittsburgh, USA,

Djupinlärning och likelihood-fri Bayesiansk inferens för stokastiska modeller

Vetenskapsrådet (VR) (2019-03924), 2020-01-01 -- 2023-12-31.

Chalmers AI-forskningscentrum (CHAIR), 2020-01-01 -- 2024-12-31.

Ämneskategorier

Sannolikhetsteori och statistik

Mer information

Senast uppdaterat

2024-09-19