LISA stochastic gravitational wave component separation with diffusion
Abstract: The numerous sources that the future space-based gravitational wave detector LISA will observe pose a unique data analysis challenge, with the most promising current avenue being a Global Fit, a simultaneous inference of all sources. This entails performing parameter estimation at an unprecedented scale, with the resolvable sources requiring up to hundreds of thousands of parameters to be estimated over the 4-year life span of the mission. Within the LISA Global fit, stochastic sources, from instrumental noise, to the galactic foreground and astrophysical or cosmological backgrounds, are particularly relevant, not only due to the astrophysical interest, but also due to their effect on the quality of the inference of all other deterministic sources. Issues such as non-gaussianity, due to poor subtraction of deterministic signals, or data gaps, scheduled and unscheduled, provide a unique opportunity for machine learning to augment traditional Bayesian methods. We present a stochastic signal inference framework for LISA data analysis, based on simulation based inference (SBI), with a state-of-the-art all-in-one framework, the Simformer. The transformer diffusion parameter-data joint inference network provides the extra level of flexibility that the data quality aspects of LISA Global Fit require.
