Skip to yearly menu bar Skip to main content


Calibrating Neural Simulation-Based Inference with Differentiable Coverage Probability

Maciej Falkiewicz · Naoya Takeishi · Imahn Shekhzadeh · Antoine Wehenkel · Arnaud Delaunoy · Gilles Louppe · Alexandros Kalousis

Great Hall & Hall B1+B2 (level 1) #714
[ ] [ Project Page ]
[ Paper [ Poster [ OpenReview
Thu 14 Dec 3 p.m. PST — 5 p.m. PST


Bayesian inference allows expressing the uncertainty of posterior belief under a probabilistic model given prior information and the likelihood of the evidence. Predominantly, the likelihood function is only implicitly established by a simulator posing the need for simulation-based inference (SBI). However, the existing algorithms can yield overconfident posteriors (Hermans et al., 2022) defeating the whole purpose of credibility if the uncertainty quantification is inaccurate. We propose to include a calibration term directly into the training objective of the neural model in selected amortized SBI techniques. By introducing a relaxation of the classical formulation of calibration error we enable end-to-end backpropagation. The proposed method is not tied to any particular neural model and brings moderate computational overhead compared to the profits it introduces. It is directly applicable to existing computational pipelines allowing reliable black-box posterior inference. We empirically show on six benchmark problems that the proposed method achieves competitive or better results in terms of coverage and expected posterior density than the previously existing approaches.

Chat is not available.