An inversion problem for optical spectrum data via physics-guided machine learning
This work addresses a challenging inverse problem in physics for researchers analyzing optical spectra, though it appears incremental as it builds on existing machine-learning approaches.
The authors tackled the problem of deriving pairing glue functions from optical spectra by proposing the regularized recurrent inference machine (rRIM), which incorporates physical principles to achieve noise robustness and reduced data requirements, yielding reliable solutions for inverse problems.
We propose the regularized recurrent inference machine (rRIM), a novel machine-learning approach to solve the challenging problem of deriving the pairing glue function from measured optical spectra. The rRIM incorporates physical principles into both training and inference and affords noise robustness, flexibility with out-of-distribution data, and reduced data requirements. It effectively obtains reliable pairing glue functions from experimental optical spectra and yields promising solutions for similar inverse problems of the Fredholm integral equation of the first kind.