Sharp minimaxity and spherical deconvolution for super-smooth error distributions

tight frame approximation for multi-frames and super-frames

در این پایان نامه یک مولد برای چند قاب یا ابر قاب تولید شده تحت عمل نمایش یکانی تصویر برای گروه های شمارش پذیر گسسته بررسی خواهد شد. مثال هایی از این قاب ها چند قاب های گابور، ابرقاب های گابور و قاب هایی برای زیرفضاهای انتقال پایاست. نشان می دهیم که مولد چند قاب تنک نرمال شده (ابرقاب) یکتا وجود دارد به طوری که مینیمم فاصله را از ان دارد. همچنین مسایل مشابه برای قاب های دوگان مطرح شده و برخی ...

Spherical Deconvolution

This paper proposes nonparametric deconvolution density estimation over S 2. Here we would think of the S 2 elements of interest being corrupted by random SO(3) elements (rotations). The resulting density on the observations would be a convolution of the SO(3) density with the true S 2 density. Consequently, the methodology, as in the Euclidean case, would be to use Fourier analysis on SO(3) an...

Localized spherical deconvolution

Optimal Spherical Deconvolution

This paper addresses the issue of optimal deconvolution density estimation on the 2-sphere. Indeed, by using the transitive group action of the rotation matrices on the 2-dimensional unit sphere, rotational errors can be introduced analogous to the Euclidean case. The resulting density turns out to be convolution in the Lie group sense and so the statistical problem is to recover the true under...

Spherical-Homoscedastic Distributions Spherical-Homoscedastic Distributions: The Equivalency of Spherical and Normal Distributions in Classification

Many feature representations, as in genomics, describe directional data where all feature vectors share a common norm. In other cases, as in computer vision, a norm or variance normalization step, where all feature vectors are normalized to a common length, is generally used. These representations and pre-processing step map the original data from R to the surface of a hypersphere Sp−1. Such re...