[Submitted on 4 Dec 2025 (v1), last revised 12 Nov 2026 (this version, v4)]
Abstract:We present a technique for posterior estimation using Normalizing Flows trained with likelihood-weighted importance sampling, the special case of neural importance sampling in which the proposal is the prior. This approach allows for the efficient inference of theoretical parameters in high-dimensional inverse problems without the need for posterior training samples. We implement the method on multi-modal benchmark tasks in 2D and 3D to check for the efficacy. A critical observation of our study is the impact of the base distribution on the modelled posteriors. We find that standard unimodal base distributions leave spurious probability textit{bridges} between well-separated modes. We demonstrate that initializing the flow with a Gaussian Mixture Model that matches the number of target modes significantly improves reconstruction fidelity, as measured by some distance and divergence metrics. Finally, we apply this method to a curated problem in heavy flavour physics — the extraction of the Wolfenstein parameters from the CP asymmetry in $B^0to J/psi,K^0$; it is multimodal, non-Gaussian, and asymmetric in its mode weights — and compare the results against a well-converged Markov Chain Monte Carlo reference and an exact reference computed by quadrature, using different metrics. Used as a proposal for importance sampling, the trained flow removes its remaining bias and gives the evidence.
Submission history
From: Rajneil Baruah [view email]
[v1] Thu, 4 Dec 2025 16:22:53 UTC (21,824 KB)
[v2] Fri, 20 Feb 2026 08:45:07 UTC (12,615 KB)
[v3] Mon, 3 Aug 2026 16:08:33 UTC (14,136 KB)
[v4] Thu, 12 Nov 2026 20:37:24 UTC (14,377 KB)
