Related papers: Likelihood-free Inference with Mixture Density Net…

Human motion prediction, which plays a key role in computer vision, generally requires a past motion sequence as input. However, in real applications, a complete and correct past motion sequence can be too expensive to achieve. In this…

The inference of physical parameters from measured distributions constitutes a core task in physics data analyses. Among recent deep learning methods, so-called conditional invertible neural networks provide an elegant approach owing to…

Likelihood-free inference methods typically make use of a distance between simulated and real data. A common example is the maximum mean discrepancy (MMD), which has previously been used for approximate Bayesian computation, minimum…

Pairwise distance-based costs are crucial for self-supervised and contrastive feature learning. Mixture Density Networks (MDNs) are a widely used approach for generative models and density approximation, using neural networks to produce…

We present a method for ultra-fast confrontation of the WMAP cosmic microwave background observations with theoretical models, implemented as a publicly available software package called CMBfit, useful for anyone wishing to measure…

In the following article we provide an exposition of exact computational methods to perform parameter inference from partially observed network models. In particular, we consider the duplication attachment (DA) model which has a likelihood…

We present a neural net algorithm for parameter estimation in the context of large cosmological data sets. Cosmological data sets present a particular challenge to pattern-recognition algorithms since the input patterns (galaxy redshift…

This paper presents a systematic literature review focusing on the application of machine learning techniques for deriving observational constraints in cosmology. The goal is to evaluate and synthesize existing research to identify…

Quasar photometric redshifts are essential for studying cosmology and large-scale structures. However, their complex spectral energy distributions cause significant redshift-color degeneracy, limiting the accuracy of traditional methods. To…

We explore the application of machine learning based on mixture density neural networks (MDNs) to the interior characterization of low-mass exoplanets up to 25 Earth masses constrained by mass, radius, and fluid Love number $k_2$. We create…

Despite the huge success of deep neural networks (NNs), finding good mechanisms for quantifying their prediction uncertainty is still an open problem. Bayesian neural networks are one of the most popular approaches to uncertainty…

We present a framework that combines physics-informed neural networks (PINNs) with Markov Chain Monte Carlo (MCMC) inference to constrain dynamical dark energy models using the Pantheon+ Type Ia supernova compilation. First, we train a…

Rapid parameter estimation is critical when dealing with short lived signals such as kilonovae. We present a parameter estimation algorithm that combines likelihood-free inference with a pre-trained embedding network, optimized to…

We present simulation-based cosmological $w$CDM inference using Dark Energy Survey Year 3 weak-lensing maps, via neural data compression of weak-lensing map summary statistics: power spectra, peak counts, and direct map-level…

High-dimensional probability density estimation for inference suffers from the "curse of dimensionality". For many physical inference problems, the full posterior distribution is unwieldy and seldom used in practice. Instead, we propose…

A common problem in beyond Standard Model phenomenology is the exploration of a multi-dimensional parameter space in view of a large number of constraints. We study and compare two methods applicable to this challenge, namely a Markov Chain…

A novel method for estimating Bayesian network (BN) parameters from data is presented which provides improved performance on test data. Previous research has shown the value of representing conditional probability distributions (CPDs) via…

This study investigates the evolution of Friedmann-Robertson-Walker (FRW) cosmological models within the $f(Q)$ gravity framework, utilizing a specific $f(Q)$ formulation and a novel Hubble parameter $H(z)$ parameterization to probe the…

Methods based on Deep Learning have recently been applied on astrophysical parameter recovery thanks to their ability to capture information from complex data. One of these methods is the approximate Bayesian Neural Networks (BNNs) which…

Identifying important features linked to a response variable is a fundamental task in various scientific domains. This article explores statistical inference for simulated Markov random fields in high-dimensional settings. We introduce a…