Related papers: Denoising Milky Way stellar survey data with norma…
AI-enhanced approaches are becoming common in astronomical data analysis, including in the galaxy morphological classification. In this study we develop an approach that enhances galaxy classification by incorporating an image denoising…
We investigate what the proposed ESA astrometric satellite GAIA will reveal by observing the halo of the Milky Way. Specifically, we look for halo streams which are the signatures left by the merging/accretion events experienced by a…
We present a panoramic map of the stellar streams of the Milky Way based upon astrometric and photometric measurements from the Gaia DR2 catalogue. In this first contribution, we concentrate on the halo at heliocentric distances beyond 5…
Denoising diffusion models have become ubiquitous for generative modeling. The core idea is to transport the data distribution to a Gaussian by using a diffusion. Approximate samples from the data distribution are then obtained by…
Sampling from unnormalized densities is analogous to the generative modeling problem, but the target distribution is defined by a known energy function instead of data samples. Because evaluating the energy function is often costly, a…
Normalizing Flows (NFs) learn invertible mappings between the data and a Gaussian distribution. Prior works usually suffer from two limitations. First, they add random noise to training samples or VAE latents as data augmentation,…
We develop a method for constraining the potential of the Milky Way using stellar streams with a known progenitor. The method expresses the stream in angle-action coordinates and integrates the orbits of the stars backwards in time to…
Large-scale astrophysics datasets present an opportunity for new machine learning techniques to identify regions of interest that might otherwise be overlooked by traditional searches. To this end, we use Classification Without Labels…
The ESA cornerstone mission Gaia was successfully launched in 2013, and is now scanning the sky to accurately measure the positions and motions of about two billion point-like sources of 3<V<20.5 mag, with the main goal of reconstructing…
The Milky Way (MW) hosts a central bar whose pattern speed, orientation, and length remain uncertain, largely due to observational biases and selection effects, despite the transformative data provided by the Gaia mission. We aim to…
The Gaia era opens new possibilities for discovering the remnants of disrupted satellite galaxies in the Solar neighborhood. If the population of local accreted stars is correlated with the dark matter sourced by the same mergers, one can…
In previous work, we developed a deep neural network classifier that only relies on phase-space information to obtain a catalog of accreted stars based on the second data release of Gaia (DR2). In this paper, we apply two clustering…
Despite the Milky Way's proximity to us, our knowledge of its dark matter halo is fairly limited, and there is still considerable uncertainty in its halo mass. Many past techniques have been limited by assumptions such as the Galaxy being…
ESA's Global Astrometric Interferometer for Astrophysics (GAIA) holds the promise of mapping out the detailed phase space structure of the Galactic halo by providing unprecedented annual proper motion and parallax of $1-10\muas$ astrometric…
Context: One of the rarest types of variability is the phenomenon of gravitational microlensing, a transient brightening of a background star due to an intervening lensing object. Microlensing is a powerful tool in studying the invisible or…
Flow-based generative modeling in continuous spaces exploit Tweedie's formula to express the denoiser (learned in training) as a score function (used in sampling). In contrast, this relation has been largely missing in the discrete setting…
Optical spectra contain a wealth of information about the physical properties and formation histories of galaxies. Often though, spectra are too noisy for this information to be accurately retrieved. In this study, we explore how machine…
We use Gaia photometry and astrometry to estimate the vertical spatial structure of the Milky Way at the Solar radius, formally accounting for sample incompleteness (the selection function) and parallax measurement uncertainty. Our results…
Gaia DR2 has delivered full-sky 6-D measurements for millions of stars, and the quest to understand the dynamics of our Galaxy has entered a new phase. Our aim is to reveal and characterize the kinematic sub-structure of the different…
Normalizing flows can transform a simple prior probability distribution into a more complex target distribution. Here, we evaluate the ability and efficiency of generative machine learning methods to sample the Boltzmann distribution of an…