$β$-Annealed Variational Autoencoder for glitches
This work addresses the challenge of efficiently managing increasing noise classes in gravitational wave detection, offering an incremental improvement in unsupervised representation learning for domain-specific applications.
The paper tackles the problem of identifying and labeling new noise gradients (glitches) in gravitational wave detectors like LIGO and Virgo, which can mask gravitational waves, by proposing a β-Annealed Variational Autoencoder (VAE) to learn representations from spectrograms in an unsupervised way, resulting in better reconstruction quality and similar disentanglement levels with one fewer hyperparameter to tune.
Gravitational wave detectors such as LIGO and Virgo are susceptible to various types of instrumental and environmental disturbances known as glitches which can mask and mimic gravitational waves. While there are 22 classes of non-Gaussian noise gradients currently identified, the number of classes is likely to increase as these detectors go through commissioning between observation runs. Since identification and labelling new noise gradients can be arduous and time-consuming, we propose $β$-Annelead VAEs to learn representations from spectograms in an unsupervised way. Using the same formulation as \cite{alemi2017fixing}, we view Bottleneck-VAEs~cite{burgess2018understanding} through the lens of information theory and connect them to $β$-VAEs~cite{higgins2017beta}. Motivated by this connection, we propose an annealing schedule for the hyperparameter $β$ in $β$-VAEs which has advantages of: 1) One fewer hyperparameter to tune, 2) Better reconstruction quality, while producing similar levels of disentanglement.