Related papers: Variational Autoencoder with Normalizing flow for …
Karyotyping is of importance for detecting chromosomal aberrations in human disease. However, chromosomes easily appear curved in microscopic images, which prevents cytogeneticists from analyzing chromosome types. To address this issue, we…
In many areas of science, complex phenomena are modeled by stochastic parametric simulators, often featuring high-dimensional parameter spaces and intractable likelihoods. In this context, performing Bayesian inference can be challenging.…
The self-lensing of a massive black hole binary (MBHB), which occurs when the two BHs are aligned close to the line of sight, is expected to produce periodic, short-duration flares. Here we study the shapes of self-lensing flares (SLFs) via…
Bayesian Neural Networks (BNNs) offer a principled and natural framework for proper uncertainty quantification in the context of deep learning. They address the typical challenges associated with conventional deep learning methods, such as…
Spectral subsampling MCMC was recently proposed to speed up Markov chain Monte Carlo (MCMC) for long stationary univariate time series by subsampling periodogram observations in the frequency domain. This article extends the approach to…
Accurate diagnosis of breast cancer in histopathology images is challenging due to the heterogeneity of cancer cell growth as well as of a variety of benign breast tissue proliferative lesions. In this paper, we propose a practical and…
Tuning of measurement models is challenging in real-world applications of sequential Monte Carlo methods. Recent advances in differentiable particle filters have led to various efforts to learn measurement models through neural networks.…
We introduce a machine learning model designed to rapidly and accurately predict the time domain gravitational wave emission of non-precessing binary black hole coalescences, incorporating the effects of higher order modes of the multipole…
Bayesian inference in the physical sciences faces a fundamental challenge: the imperative for high-fidelity physical modeling often clashes with the intrinsic limitations of stochastic sampling algorithms. Complex, high-dimensional…
Microlensing is one of the most promising tools for discovering stellar-mass black holes (BHs) in the Milky Way because it allows us to probe dark or faint celestial compact objects. While the existence of stellar-mass BHs has been…
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…
The ringdown signal following a black hole (BH) merger can be modeled as a superposition of BH quasinormal modes (QNMs), offering a clean setup for testing gravitational theories. In particular, detecting multiple QNMs enables consistency…
A multi-configuration mixing approach built on essentially complex, symmetry-projected Hartree-Fock-Bogoliubov (HFB) mean fields is introduced. The mean fields are obtained by variation after projection. The configuration space consists out…
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…
Broad-band spectra of accreting X-ray binary pulsars can be fit by a phenomenological model composed by a power law with a high energy rollover above 10 keV, plus a blackbody component with a temperature of few hundred eV. While, at least…
We propose a variational autoencoder (VAE) approach for parameter estimation in nonlinear mixed-effects models based on ordinary differential equations (NLME-ODEs) using longitudinal data from multiple subjects. In moderate dimensions,…
A machine-learning-based method is developed to identify objects with unusual stellar spectra. The method employs an autoencoder, a neural network trained to compress spectral data into a low-dimensional representation and subsequently…
We introduce a novel method to generate a bank of gravitational-waveform templates of binary black hole (BBH) mergers for matched-filter searches in LIGO, Virgo and Kagra data.We derive a novel expression for the metric approximation to the…
We extend variational autoencoders (VAEs) to collaborative filtering for implicit feedback. This non-linear probabilistic model enables us to go beyond the limited modeling capacity of linear factor models which still largely dominate…
Conditional belief networks introduce stochastic binary variables in neural networks. Contrary to a classical neural network, a belief network can predict more than the expected value of the output $Y$ given the input $X$. It can predict a…