Results 11 to 20 of about 807,423 (305)
Scale Mixture of Rayleigh Distribution [PDF]
Mathematics, 2020 In this paper, the scale mixture of Rayleigh (SMR) distribution is introduced. It is proven that this new model, initially defined as the quotient of two independent random variables, can be expressed as a scale mixture of a Rayleigh and a particular ...
Pilar A. Rivera +3 more
doaj +6 more sources
Scale Mixture of Gaussian Modelling of Polarimetric SAR Data
EURASIP Journal on Advances in Signal Processing, 2010 This paper describes a flexible non-Gaussian statistical method used to model polarimetric synthetic aperture radar (POLSAR) data. We outline the theoretical basis of the well-know product model as described by the class of Scale Mixture models and ...
Anthony P. Doulgeris +1 more
doaj +2 more sources
Conditional limits of Wp scale mixture distributions [PDF]
Journal of Statistical Planning and Inference, 2009 In this paper we introduce the class of W_p scale mixture random vectors with a particular radial decomposition and a independent splitting property specified by some random variable W_p, and a positive constant p. We derive several conditional limit results assuming that the distribution of the random radius is in the max-domain of attraction of a ...
Hashorva, Enkelejd
core +5 more sources
Gaussian approximation of Gaussian scale mixtures [PDF]
Kybernetika, 2021 For a given positive random variable $V>0$ and a given $Z\sim N(0,1)$ independent of $V$, we compute the scalar $t_0$ such that the distance between $Z\sqrt{V}$ and $Z\sqrt{t_0}$ in the $L^2(\R)$ sense, is minimal. We also consider the same problem in several dimensions when $V$ is a random positive definite matrix.
Gérard Letac, Hélène Massam
openaire +2 more sources
Image denoising using mixtures of Gaussian scale mixtures [PDF]
2008 15th IEEE International Conference on Image Processing, 2008 The local statistical properties of photographic images, when represented in a multi-scale basis, have been described using Gaussian scale mixtures (GSMs). In that model, each spatial neighborhood of coefficients is described as a Gaussian random vector modulated by a random hidden positive scaling variable.
Jose A. Guerrero-Colon +2 more
openaire +1 more source
Image Denoising Using Mixtures of Projected Gaussian Scale Mixtures [PDF]
IEEE Transactions on Image Processing, 2009 We propose a new statistical model for image restoration in which neighborhoods of wavelet subbands are modeled by a discrete mixture of linear projected Gaussian Scale Mixtures (MPGSM). In each projection, a lower dimensional approximation of the local neighborhood is obtained, thereby modeling the strongest correlations in that neighborhood.
Bart Goossens +2 more
openaire +2 more sources
Tutel: Adaptive Mixture-of-Experts at Scale
CoRR, 2022 Sparsely-gated mixture-of-experts (MoE) has been widely adopted to scale deep learning models to trillion-plus parameters with fixed computational cost. The algorithmic performance of MoE relies on its token routing mechanism that forwards each input token to the right sub-models or experts.
Changho Hwang +14 more
openaire +3 more sources
A multiscale finite element method for soil-rock mixture
Frontiers in Materials, 2023 Soil-rock mixture is a complex multi-phase composite geotechnical material, and its strength is determined by the physical properties of constituent multi-phase materials and their coupling mechanical response between different phases of materials. Based
Jia Liu, Deluan Feng
doaj +1 more source
Image restoration via exponential scale mixture‐based simultaneous sparse prior
IET Image Processing, 2022 Image prior plays a decisive role in the performance of widely studied model‐based restoration methods. To further improve restoration performance, this paper proposes an exponential scale mixture‐based simultaneous sparse prior (ESM‐SSP) to accurately ...
Wei Yuan, Han Liu, Lili Liang
doaj +1 more source
Scale Mixtures Distributions in Insurance Applications [PDF]
ASTIN Bulletin, 2003 In this paper non-normal distributions via scale mixtures are introduced into insurance applications. The symmetric distributions of interest are the Student- t and exponential power ( EP ) distributions.
Choy, S. T. Boris, Chan, C. M.
openaire +1 more source