The distortion of the quantizer built from a n-sample of a probability distribution over a vector space with the famous k-means algorithm is firstly studied in this thesis report. To be more precise, this report aims to give oracle inequalities on the difference between the distortion of the k-means quantizer and the minimum distortion achievable by a k-point quantizer, where the influence of the natural parameters of the quantization issue should be precisely described. For instance, some natural parameters are the distribution support, the size k of the quantizer set of images, the dimension of the underlying Euclidean space, and the sample size n. After a brief summary of the previous works on this topic, an equivalence between the condi...
54 pagesWe present an introductory survey to optimal vector quantization and its first applications ...
Modern data analysis provides scientists with statistical and machine learning algorithms with impre...
This thesis studies MMSE estimation on the basis of quantized noisy observations. It presents nonas...
The distortion of the quantizer built from a n-sample of a probability distribution over a vector sp...
The distortion of the quantizer built from a n-sample of a probability distribution over a vector sp...
Ce manuscrit étudie dans un premier temps la dépendance de la distorsion, ou erreur en quantificatio...
Though mostly used as a clustering algorithm, k-means are originally designed as a quantization algo...
Three topics are explored in this thesis: inference in high-dimensional multi-task regression, geome...
La qualité de la quantification vectorielle (VQ) utilisant l'algorithme de Linde, Buzo et Gray et la...
AbstractQuantization consists in studying the Lr-error induced by the approximation of a random vect...
National audienceNous proposons de décrire la conception d'un nouveau quantificateur vectoriel pour ...
International audienceQuantization, defined as the act of attributing a finite number of levels to a...
Dans la première partie, nous nous concentrons sur la quantification vectorielle gloutonne. Nous éta...
25p.International audienceWe elucidate the asymptotics of the L^s-quantization error induced by a se...
The effect of errors in variables in quantization is investigated. We prove general exact and non-ex...
54 pagesWe present an introductory survey to optimal vector quantization and its first applications ...
Modern data analysis provides scientists with statistical and machine learning algorithms with impre...
This thesis studies MMSE estimation on the basis of quantized noisy observations. It presents nonas...
The distortion of the quantizer built from a n-sample of a probability distribution over a vector sp...
The distortion of the quantizer built from a n-sample of a probability distribution over a vector sp...
Ce manuscrit étudie dans un premier temps la dépendance de la distorsion, ou erreur en quantificatio...
Though mostly used as a clustering algorithm, k-means are originally designed as a quantization algo...
Three topics are explored in this thesis: inference in high-dimensional multi-task regression, geome...
La qualité de la quantification vectorielle (VQ) utilisant l'algorithme de Linde, Buzo et Gray et la...
AbstractQuantization consists in studying the Lr-error induced by the approximation of a random vect...
National audienceNous proposons de décrire la conception d'un nouveau quantificateur vectoriel pour ...
International audienceQuantization, defined as the act of attributing a finite number of levels to a...
Dans la première partie, nous nous concentrons sur la quantification vectorielle gloutonne. Nous éta...
25p.International audienceWe elucidate the asymptotics of the L^s-quantization error induced by a se...
The effect of errors in variables in quantization is investigated. We prove general exact and non-ex...
54 pagesWe present an introductory survey to optimal vector quantization and its first applications ...
Modern data analysis provides scientists with statistical and machine learning algorithms with impre...
This thesis studies MMSE estimation on the basis of quantized noisy observations. It presents nonas...