Bayesian inference with likelihood reweighting: motivation, method, and application to gravitational-wave astrophysics

Add to your list(s) Download to your calendar using vCal

• Isobel Romero-Shaw (DAMTP)
• Thursday 10 November 2022, 13:00-14:30
• Hoyle Lecture Theatre, Institute of Astronomy, Madingley Rise.

If you have a question about this talk, please contact James Fergusson.

Bayesian inference is the workhorse of gravitational-wave astrophysics. By analysing a gravitational-wave signal with computational Bayesian methods, we obtain a posterior probability distribution the high-dimensional parameter space that describes its source. This relies on computationally-intensive models for the signal, which must be sufficiently efficient that they can be evaluated hundreds of thousands of times per event. In the case that the model is not sufficiently efficient, there is a shortcut: likelihood reweighting. In this talk, I introduce Bayes theorem and show how it is implemented for gravitational-wave astrophysics. I demonstrate the logic behind likelihood reweighting, and explore the different situations in which it can be useful. I also give examples of the successful use of likelihood reweighting to measure the properties of gravitational-wave sources.

This talk is part of the Data Intensive Science Seminar Series series.

This talk is included in these lists:

• Cambridge Astronomy Talks
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge talks
• Chris Davis' list
• Combined External Astrophysics Talks DAMTP
• Cosmology, Astrophysics and General Relativity
• Hoyle Lecture Theatre, Institute of Astronomy, Madingley Rise
• Institute of Astronomy Extra Talks
• Institute of Astronomy Talk Lists
• Interested Talks
• Titel: TBC
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.