Related papers: A COMPASS to Model Comparison and Simulation-Based…
Automatic structure elucidation is essential for self-driving laboratories as it enables the system to achieve truly autonomous. This capability closes the experimental feedback loop, ensuring that machine learning models receive reliable…
Statistical inference on the explained variation of an outcome by a set of covariates is of particular interest in practice. When the covariates are of moderate to high-dimension and the effects are not sparse, several approaches have been…
Motivated by the inability of Galactic chemical evolution models to reproduce some of the observed solar neighbourhood distribution of elements (and isotopes) with atomic numbers 6 < Z < 15, we have revisited the relevant stellar and…
We present a new algorithm for identifying superbubbles in HI column density maps of both observed and simulated galaxies that has only a single adjustable parameter. The algorithm includes an automated galaxy-background separation step to…
This paper addresses the challenging problem of category-level pose estimation. Current state-of-the-art methods for this task face challenges when dealing with symmetric objects and when attempting to generalize to new environments solely…
We present the marginal unbiased score expansion (MUSE) method, an algorithm for generic high-dimensional hierarchical Bayesian inference. MUSE performs approximate marginalization over arbitrary non-Gaussian latent parameter spaces,…
Modelling of large-scale structure is increasingly concerned with galaxy assembly bias (GAB), the dependence of galaxy clustering on quantities other than halo mass. We investigate how baryonic physics affects the strength and redshift…
Future cosmological galaxy surveys such as the Large Synoptic Survey Telescope (LSST) will photometrically observe very large numbers of galaxies. Without spectroscopy, the redshifts required for the analysis of these data will need to be…
We develop a new efficient methodology for Bayesian global sensitivity analysis for large-scale multivariate data. The focus is on computationally demanding models with correlated variables. A multivariate Gaussian process is used as a…
Although linear regression models are fundamental tools in statistical science, the estimation results can be sensitive to outliers. While several robust methods have been proposed in frequentist frameworks, statistical inference is not…
Flagship near-future surveys targeting $10^8-10^9$ galaxies across cosmic time will soon reveal the processes of galaxy assembly in unprecedented resolution. This creates an immediate computational challenge on effective analyses of the…
Diffusion models provide a powerful way to incorporate complex prior information for solving inverse problems. However, existing methods struggle to correctly incorporate guidance from conflicting signals in the prior and measurement, and…
We consider cosmological applications of galaxy number density correlations to be inferred from future deep and wide multi-band optical surveys. We mostly focus on very large scales as a probe of possible features in the primordial power…
We present Nested Sampling with Slice-within-Gibbs (NS-SwiG), an algorithm for Bayesian inference and evidence estimation in high-dimensional models whose likelihood admits a factorization, such as hierarchical Bayesian models. We construct…
Simulation based inference has seen increasing interest in the past few years as a promising approach to model the non linear scales of galaxy clustering. The common approach using Gaussian process is to train an emulator over the…
In this lecture I will introduce the concept of galactic chemical evolution, namely the study of how and where the chemical elements formed and how they were distributed in the stars and gas in galaxies. The main ingredients to build models…
Upcoming facilities such as the Herschel Space Observatory or ALMA will deliver a wealth of molecular line observations of young stellar objects (YSOs). Based on line fluxes, chemical abundances can then be estimated by radiative transfer…
The solar s-process abundances have been analyzed in the framework of a Galactic Chemical Evolution (GCE) model. The aim of this work is to implement the study by Bisterzo et al. (2014), who investigated the effect of one of the major…
The recent availability of huge, many-dimensional data sets, like those arising from genome-wide association studies (GWAS), provides many opportunities for strengthening causal inference. One popular approach is to utilize these…
Covariance matrix estimation is a fundamental statistical task in many applications, but the sample covariance matrix is sub-optimal when the sample size is comparable to or less than the number of features. Such high-dimensional settings…