相关论文: Machine learning constraints on deviations from ge…

An algorithm is described that adaptively learns a non-linear mutation distribution. It works by training a denoising autoencoder (DA) online at each generation of a genetic algorithm to reconstruct a slowly decaying memory of the best…

In this paper, we propose a novel normalization method called gradient normalization (GN) to tackle the training instability of Generative Adversarial Networks (GANs) caused by the sharp gradient space. Unlike existing work such as gradient…

In this paper we directly constrain possible spatial variations of the Newtonian gravitational constant G over ranges 0.01-5 AU in various extrasolar multi-planet systems. By means of the third Kepler's law we determine the quantity \Gamma_…

The optimization of structural parameters, such as mass(m), stiffness(k), and damping coefficient(c), is critical for designing efficient, resilient, and stable structures. Conventional numerical approaches, including Finite Element Method…

We consider the problem of data augmentation, i.e., generating artificial samples to extend a given corpus of training data. Specifically, we propose attributed-guided augmentation (AGA) which learns a mapping that allows to synthesize data…

In this work, we investigate the General Relativistic Entropic Acceleration (GREA) framework, in which late-time acceleration emerges from entropy production associated with the cosmological horizon, and compare its performance with the…

Constraints on a dark energy dominated Universe are obtained from an interplay between Bayesian Machine Learning and string Swampland criteria. The approach here differs from previous studies, since in the generative process Swampland…

In adversarial machine learning, deep neural networks can fit the adversarial examples on the training dataset but have poor generalization ability on the test set. This phenomenon is called robust overfitting, and it can be observed when…

Generating synthetic data for financial time series poses challenges, especially considering their non-stationary nature. Traditional statistical time series models normally assume weak stationarity. However, this assumption can constrain…

In this paper we place observational constraints on the well-known $\gamma$-gravity $f(R)$ model using the latest cosmological data, namely we use the latest growth rate, Cosmic Microwave Background, Baryon Acoustic Oscillations, Supernovae…

We explore the potential variation of two fundamental constants, the fine-structure constant $\alpha$ and the proton-to-electron mass ratio $\mu$, within the framework of modified gravity theories and finite-temperature effects. Utilising…

The susceptibility of deep neural networks to untrustworthy predictions, including out-of-distribution (OOD) data and adversarial examples, still prevent their widespread use in safety-critical applications. Most existing methods either…

While deep learning has resulted in major breakthroughs in many application domains, the frameworks commonly used in deep learning remain fragile to artificially-crafted and imperceptible changes in the data. In response to this fragility,…

In this work, we present an extension of the genetic algorithm (GA) which exploits the supervised learning technique called active subspaces (AS) to evolve the individuals on a lower dimensional space. In many cases, GA requires in fact…

Machine learning models struggle with generalization when encountering out-of-distribution (OOD) samples with unexpected distribution shifts. For vision tasks, recent studies have shown that test-time adaptation employing diffusion models…

We explore observational constraints on possible deviations from Newtonian gravity by means of large-scale clustering of galaxies. We measure the power spectrum and the bispectrum of Sloan Digital Sky Survey galaxies and compare the result…

Recent analyses \cite{Nesseris:2017vor,Kazantzidis:2018rnb} have indicated that an effective Newton's constant $G_{\rm eff}(z)$ decreasing with redshift may relieve the observed tension between the Planck15 best fit $\Lambda$CDM…

General Relativistic Entropic Acceleration (GREA) theory provides a covariant formalism for out-of-equilibrium phenomena in GR, extending the Einstein equations with an entropic force that behaves like bulk viscosity with a negative…

We investigate uncertainties in the estimation of the Hubble constant ($H_0$) arising from Gaussian Process (GP) reconstruction, demonstrating that the choice of kernel introduces systematic variations comparable to those arising from…

Nowadays, thanks to the improved precision of cosmological data, it has been possible to search for deviation from the general relativity theory with tests on large cosmic scales. Particularly, there is a class of modified gravity theories…