Related papers: $\beta$-Annealed Variational Autoencoder for glitc…

Through training on unlabeled data, anomaly detection has the potential to impact computer-aided diagnosis by outlining suspicious regions. Previous work on deep-learning-based anomaly detection has primarily focused on the reconstruction…

Gravitational waves from binary neutron star post-merger remnants have the potential to uncover the physics of the hot nuclear equation of state. These gravitational-wave signals are high frequency ($\sim$ kHz) and short lived…

Generative Adversarial Networks (GANs) play an increasingly important role in machine learning. However, there is one fundamental issue hindering their practical applications: the absence of capability for encoding real-world samples. The…

Variational Graph Auto-Encoders (VGAEs) have been widely used to solve the node clustering task. However, the state-of-the-art methods have numerous challenges. First, existing VGAEs do not account for the discrepancy between the inference…

Data-driven fault diagnostics of safety-critical systems often faces the challenge of a complete lack of labeled data associated with faulty system conditions (i.e., fault types) at training time. Since an unknown number and nature of fault…

Data-driven reduced-order models based on autoencoders generally lack interpretability compared to classical methods such as the proper orthogonal decomposition. More interpretability can be gained by disentangling the latent variables and…

Non-Gaussian noise in gravitational-wave detectors, known as "glitches," can bias the inferred parameters of transient signals when they occur nearby in time and frequency. These biases are addressed with a variety of methods that remove or…

Data from the LIGO detectors typically contain many non-Gaussian noise transients which arise due to instrumental and environmental conditions. These non-Gaussian transients can be an issue for the modelled and unmodelled transient…

Variational autoencoders (VAEs) are essential tools in end-to-end representation learning. However, the sequential text generation common pitfall with VAEs is that the model tends to ignore latent variables with a strong auto-regressive…

Graph representation learning is a fundamental research issue in various domains of applications, of which the inductive learning problem is particularly challenging as it requires models to generalize to unseen graph structures during…

Graph anomaly detection faces significant challenges due to the scarcity of reliable anomaly-labeled datasets, driving the development of unsupervised methods. Graph autoencoders (GAEs) have emerged as a dominant approach by reconstructing…

Variational Auto-Encoders (VAEs) have become very popular techniques to perform inference and learning in latent variable models as they allow us to leverage the rich representational power of neural networks to obtain flexible…

Model-agnostic anomaly detection is one of the promising approaches in the search for new beyond the standard model physics. In this paper, we present Set-VAE, a particle-based variational autoencoder (VAE) anomaly detection algorithm. We…

Gravitational wave science should transform in this decade from a study of what has not been seen to a full-fledged field of astronomy in which detected signals reveal the nature of cataclysmic events and exotic objects. The LIGO Scientific…

Learning disentangled representations without supervision or inductive biases, often leads to non-interpretable or undesirable representations. On the other hand, strict supervision requires detailed knowledge of the true generative…

We present a novel machine-learning approach to estimate selection effects in gravitational-wave observations. Using techniques similar to those commonly employed in image classification and pattern recognition, we train a series of…

Adaptive variational quantum eigensolvers (ADAPT-VQEs) are promising candidates for simulations of strongly correlated systems on near-term quantum hardware. To further improve the noise resilience of these algorithms, recent efforts have…

Gravitational wave detectors like the Einstein Telescope and LISA generate long multivariate time series, which pose significant challenges in spectral density estimation due to a number of overlapping signals as well as the presence of…

While gravitational waves have been detected from mergers of binary black holes and binary neutron stars, signals from core collapse supernovae, the most energetic explosions in the modern Universe, have not been detected yet. Here we…

Gravitational waves from binary black hole and neutron star mergers are being regularly detected. As of 2021, ninety confident gravitational wave detections have been made by the LIGO and Virgo detectors. Work is ongoing to further increase…