Deep neural network driven simulation based inference method for pole position estimation under model misspecification

The method of simulation based inference is shown to lead to a more accurate resonance parameter estimation than traditional χ 2 minimization in certain cases of model misspecification in a case-study of π π scattering and the ρ ( 770 ) -resonance. Models fit to certain datasets using χ 2 minimization can make inaccurate predictions for the pole position of the ρ ( 770 ) . Simulation based inference (SBI) is shown to make a more robust predictions for the pole positions. This is significant, both as a proof of concept that the SBI method can be used in cases of model misspecification, and because models of π π scattering are a crucial part to many physical systems of contemporary interest [ a 1 ( 1260 ) , ω ( 782 ) etc.].