Related papers: Learning Theory Informed Priors for Bayesian Infer…

In this study, a machine learning-based technique is developed to reduce the computational cost required to explore large design spaces of substitutional alloys. The first advancement is based on a neural network approach to predict the…

We introduce an evidence-driven Bayesian formulation of physics-informed neural networks that enables automatic optimization of loss weights between PDE residuals, boundary conditions, and observational data. Unlike existing Bayesian PINN…

The presented paper is a comprehensive analysis of two dark energy (DE) cosmological models wherein exact solutions of the Einstein field equations (EFEs) are obtained in a model-independent way (or by cosmological parametrization). A…

A promising idea to resolve the long standing Hubble tension is to postulate a new subdominant dark-energy-like component in the pre-recombination Universe which is traditionally termed as the Early Dark Energy (EDE). However, as shown in…

Sparse modeling for signal processing and machine learning has been at the focus of scientific research for over two decades. Among others, supervised sparsity-aware learning comprises two major paths paved by: a) discriminative methods and…

The recent cosmological picture contains a significant tension indicating that our standard $\Lambda$CDM picture may be incomplete. Early Dark Energy models can alleviate the Hubble tension, by assuming an early acceleration that could…

Generative diffusion models can provide powerful prior probability models for inverse problems in imaging, but existing implementations suffer from two key limitations: $(i)$ the prior density is represented implicitly, and $(ii)$ they rely…

Latent space Energy-Based Models (EBMs), also known as energy-based priors, have drawn growing interests in generative modeling. Fueled by its flexibility in the formulation and strong modeling power of the latent space, recent works built…

The interpretation of data in terms of multi-parameter models of new physics, using the Bayesian approach, requires the construction of multi-parameter priors. We propose a construction that uses elements of Bayesian reference analysis. Our…

We examine the use of a novel variant of Physics-Informed Neural Networks to predict cosmological parameters from recent supernovae and baryon acoustic oscillations (BAO) datasets. Our machine learning framework generates uncertainty…

The Bayesian update step poses significant computational challenges in high-dimensional nonlinear estimation. While log-homotopy particle flow filters offer an alternative to stochastic sampling, existing formulations usually yield stiff…

This work proposes a solution for the problem of training physics-informed networks under partial integro-differential equations. These equations require an infinite or a large number of neural evaluations to construct a single residual for…

Uncertainty quantification in reinforcement learning can greatly improve exploration and robustness. Approximate Bayesian approaches have recently been popularized to quantify uncertainty in model-free algorithms. However, so far the focus…

This manuscript revisits the phenomenological emergent dark energy model (PEDE) by confronting it with recent cosmological data from early and late times. In particular we analyze PEDE model by using the baryon acoustic oscillation (BAO)…

Early dark energy (EDE) is one of the most promising possibilities in order to resolve the Hubble tension: the discrepancy between early and late-Universe measurements of the Hubble constant. In this paper we propose a model of a scalar…

(abridged)Cosmological observational programs often compare their data not only with $\Lambda$CDM, but also with extensions applying dynamical models of dark energy (DDE), with a time-dependent equation of state (EoS) parameter $w$. We…

A key sticking point of Bayesian analysis is the choice of prior distribution, and there is a vast literature on potential defaults including uniform priors, Jeffreys' priors, reference priors, maximum entropy priors, and weakly informative…

In this work, we propose a novel prior learning method for advancing generalization and uncertainty estimation in deep neural networks. The key idea is to exploit scalable and structured posteriors of neural networks as informative priors…

We present an analysis of DESI Data Release 1 (DR1) that incorporates Halo Occupation Distribution (HOD)-informed priors into Full-Shape (FS) modeling of the power spectrum based on cosmological perturbation theory (PT). By leveraging…

Class imbalance induces systematic bias in deep neural networks by imposing a skewed effective class prior. This work introduces the Neural Prior Estimator (NPE), a framework that learns feature-conditioned log-prior estimates from latent…