Here, I will store useful references for gravitational waves. This page was inspired by this compilation of references, which focuses on using machine learning in GW.

Textbooks

I still have to look for good references myself - check back soon!

Papers

Fast gravitational wave parameter estimation without compromises (link):

Parameter estimation for GWs relies on matched filtering. To sample the posterior, the authors develop a new framework, which implements several techniques. Most exciting is the use of normalizing flows which allows them to approximate the posterior distribution using neural networks and use that as a proposal distribution to generate the samples. PE usually takes days or weeks of sampling time, but this paper reduces it to an astonishing single minute.

Genetic-algorithm-optimized neural networks for gravitational wave classification (link):

The authors make use of genetic algorithms to design new neural network architectures for GW classification, specifically CNNs for matched filtering. They offer a very nice introduction to genetic algorithms and deep learning, for those new to these topics. They start from an existing network, and are able to find a new architecture with 78% fewer trainable parameters while obtaining an 11% increase in accuracy. The downside is that this search for new architectures requires massive amount of computation power, which is infeasibe unless HPC is used.