Related papers: Learning novel representations of variable sources…
Variational autoencoders (VAEs) are widely used deep generative models capable of learning unsupervised latent representations of data. Such representations are often difficult to interpret or control. We consider the problem of…
A variational autoencoder (VAE) is a probabilistic machine learning framework for posterior inference that projects an input set of high-dimensional data to a lower-dimensional, latent space. The latent space learned with a VAE offers…
Context. A large fraction of Asymptotic Giant Branch (AGB) stars develop carbon-rich atmospheres during their evolution. Based on their color and luminosity, these carbon stars can be easily distinguished from many other kinds of stars.…
Context. Gaia Early Data Release 3 (EDR3), published in December 2020, features improved photometry and astrometry over that published in the previous DR2 file, and includes a substantially larger number of sources, of the order of 2,000…
Generative models have emerged as powerful tools in medical imaging, enabling tasks such as segmentation, anomaly detection, and high-quality synthetic data generation. These models typically rely on learning meaningful latent…
The Gaia DR2 sample of short-timescale variable candidates results from the investigation of the first 22 months of Gaia photometry for a subsample of sources at the Gaia faint end. For this exercise, we limited ourselves to the case of…
Gaia Early Data Release 3 (Gaia EDR3) contains results for 1.812 billion sources in the magnitude range G = 3 to 21 based on observations collected by the European Space Agency Gaia satellite during the first 34 months of its operational…
Variational autoencoders (VAEs) are powerful deep generative models widely used to represent high-dimensional complex data through a low-dimensional latent space learned in an unsupervised manner. In the original VAE model, the input data…
The third Gaia data release is published in two stages. The early part, Gaia EDR3, gives very precise astrometric and photometric properties for nearly two billion sources together with seven million radial velocities from Gaia DR2. The…
Supermassive black hole binaries (SMBHB) are expected to produce periodic modulations in active galactic nuclei (AGN) light curves, but distinguishing such signals from stochastic red-noise variability remains a major challenge. We present…
In this paper, we explore the feasibility of using machine learning regression as a method of extracting basic stellar parameters and line-of-sight extinctions from spectro-photometric data. We built a stable gradient-boosted random-forest…
Detectors in next-generation high-energy physics experiments face several daunting requirements, such as high data rates, damaging radiation exposure, and stringent constraints on power, space, and latency. To address these challenges,…
We present the early installment of the third Gaia data release, Gaia EDR3, consisting of astrometry and photometry for 1.8 billion sources brighter than magnitude 21, complemented with the list of radial velocities from Gaia DR2. Gaia EDR3…
The ability to generate physically plausible ensembles of variable sources is critical to the optimization of time-domain survey cadences and the training of classification models on datasets with few to no labels. Traditional data…
The discovery of new materials is often constrained by the need for large labelled datasets or expensive simulations. In this study, we explore the use of Disentangling Autoencoders (DAEs) to learn compact and interpretable representations…
The Gaia third Data Release (DR3) presents a catalogue of 474\,026 stars with variability induced by magnetic activity. For each star, the catalogue provides a list of about 70 parameters among which the most important are the stellar…
Variational Autoencoders (VAEs) are well-established as a principled approach to probabilistic unsupervised learning with neural networks. Typically, an encoder network defines the parameters of a Gaussian distributed latent space from…
The ability to accurately model random fields plays a critical role in science and engineering for problems involving uncertain, spatially-varying quantities such as heterogeneous material properties and turbulent flows. Deep generative…
Gaia Data Release 3 provides novel flux-calibrated low-resolution spectrophotometry for about 220 million sources in the wavelength range 330nm - 1050nm (XP spectra). Synthetic photometry directly tied to a flux in physical units can be…
The third gaia data release (DR3) provides a wealth of new data products. The early part of the release, Gaia EDR3, already provided the astrometric and photometric data for nearly two billion sources. The full release now adds improved…