Let H be a separable Hilbert space over the complex field. The class S := {N|M : N is normal on H and M is an invariant subspace for Ng of subnormal operators. This notion was introduced by Halmos. The minimal normal extension Ň of a subnormal operator S was introduced by σ (S) and then Bram proved that Halmos. Halmos proved that σ(Ň) (S) is obtained by filling certain number of holes in the spectrum (Ň) of the minimal normal extension Ň of a subnormal operator S. Let σ (S) := σ (Ň) be the spectrum of the minimal normal extension Ň of S; which is called the normal spectrum of a subnormal operator S: This notion is due to Abrahamse and Douglas. We give several well-known characterization of subnormality. Let C* (S1) and C* (S2) be the C*- algebras generated by S1 and S2 respectively, where S1 and S2 are bounded operators on H: Next we give a characterization for subnormality which is purely C - algebraic. We also establish an intrinsic characterization of the normal spectrum for a subnormal operator, which enables us to answer the fol-lowing two questions. Let II be a *- representation from C* (S1) onto C* (S2) such that II(S1) = S2. If S1 is subnormal, then does it follow that S2 is subnormal? What is the relation between σ (S1) and σ (S2)? The first question was asked by Bram and second was asked by Abrahamse and Douglas. Answers to these questions were given by Bunce and Deddens.

Le but de l’apprentissage supervisé est d’inférer des relations entre un phénomène que l’on souhaite prédire et des variables « explicatives ». À cette fin, on dispose d’observations de multiples réalisations du phénomène, à partir desquelles on propose une règle de prédiction. L’émergence récente de sources de données à très grande échelle, tant par le nombre d’observations effectuées (en analyse d’image, par exemple) que par le grand nombre de variables explicatives (en génétique), a fait émerger deux difficultés : d’une part, il devient difficile d’éviter l’écueil du sur-apprentissage lorsque le nombre de variables explicatives est très supérieur au nombre d’observations; d’autre part, l’aspect algorithmique devient déterminant, car la seule résolution d’un système linéaire dans les espaces en jeupeut devenir une difficulté majeure. Des algorithmes issus des méthodes d’approximation stochastique proposent uneréponse simultanée à ces deux difficultés : l’utilisation d’une méthode stochastique réduit drastiquement le coût algorithmique, sans dégrader la qualité de la règle de prédiction proposée, en évitant naturellement le sur-apprentissage. En particulier, le cœur de cette thèse portera sur les méthodes de gradient stochastique. Les très populaires méthodes paramétriques proposent comme prédictions des fonctions linéaires d’un ensemble choisi de variables explicatives. Cependant, ces méthodes aboutissent souvent à une approximation imprécise de la structure statistique sous-jacente. Dans le cadre non-paramétrique, qui est un des thèmes centraux de cette thèse, la restriction aux prédicteurs linéaires est levée. La classe de fonctions dans laquelle le prédicteur est construit dépend elle-même des observations. En pratique, les méthodes non-paramétriques sont cruciales pour diverses applications, en particulier pour l’analyse de données non vectorielles, qui peuvent être associées à un vecteur dans un espace fonctionnel via l’utilisation d’un noyau défini positif. Cela autorise l’utilisation d’algorithmes associés à des données vectorielles, mais exige une compréhension de ces algorithmes dans l’espace non-paramétrique associé : l’espace à noyau reproduisant. Par ailleurs, l’analyse de l’estimation non-paramétrique fournit également un éclairage révélateur sur le cadre paramétrique, lorsque le nombre de prédicteurs surpasse largement le nombre d’observations. La première contribution de cette thèse consiste en une analyse détaillée de l’approximation stochastique dans le cadre non-paramétrique, en particulier dans le cadre des espaces à noyaux reproduisants. Cette analyse permet d’obtenir des taux de convergence optimaux pour l’algorithme de descente de gradient stochastique moyennée. L’analyse proposée s’applique à de nombreux cadres, et une attention particulière est portée à l’utilisation d’hypothèses minimales, ainsi qu’à l’étude des cadres où le nombre d’observations est connu à l’avance, ou peut évoluer. La seconde contribution est de proposer un algorithme, basé sur un principe d’accélération, qui converge à une vitesse optimale, tant du point de vue de l’optimisation que du point de vue statistique. Cela permet, dans le cadre non-paramétrique, d’améliorer la convergence jusqu’au taux optimal, dans certains régimes pour lesquels le premier algorithme analysé restait sous-optimal. Enfin, la troisième contribution de la thèse consiste en l’extension du cadre étudié au delà de la perte des moindres carrés : l’algorithme de descente de gradient stochastiqueest analysé comme une chaine de Markov. Cette approche résulte en une interprétation intuitive, et souligne les différences entre le cadre quadratique et le cadre général. Une méthode simple permettant d’améliorer substantiellement la convergence est également proposée. / The goal of supervised machine learning is to infer relationships between a phenomenon one seeks to predict and “explanatory” variables. To that end, multiple occurrences of the phenomenon are observed, from which a prediction rule is constructed. The last two decades have witnessed the apparition of very large data-sets, both in terms of the number of observations (e.g., in image analysis) and in terms of the number of explanatory variables (e.g., in genetics). This has raised two challenges: first, avoiding the pitfall of over-fitting, especially when the number of explanatory variables is much higher than the number of observations; and second, dealing with the computational constraints, such as when the mere resolution of a linear system becomes a difficulty of its own. Algorithms that take their roots in stochastic approximation methods tackle both of these difficulties simultaneously: these stochastic methods dramatically reduce the computational cost, without degrading the quality of the proposed prediction rule, and they can naturally avoid over-fitting. As a consequence, the core of this thesis will be the study of stochastic gradient methods. The popular parametric methods give predictors which are linear functions of a set ofexplanatory variables. However, they often result in an imprecise approximation of the underlying statistical structure. In the non-parametric setting, which is paramount in this thesis, this restriction is lifted. The class of functions from which the predictor is proposed depends on the observations. In practice, these methods have multiple purposes, and are essential for learning with non-vectorial data, which can be mapped onto a vector in a functional space using a positive definite kernel. This allows to use algorithms designed for vectorial data, but requires the analysis to be made in the non-parametric associated space: the reproducing kernel Hilbert space. Moreover, the analysis of non-parametric regression also sheds some light on the parametric setting when the number of predictors is much larger than the number of observations. The first contribution of this thesis is to provide a detailed analysis of stochastic approximation in the non-parametric setting, precisely in reproducing kernel Hilbert spaces. This analysis proves optimal convergence rates for the averaged stochastic gradient descent algorithm. As we take special care in using minimal assumptions, it applies to numerous situations, and covers both the settings in which the number of observations is known a priori, and situations in which the learning algorithm works in an on-line fashion. The second contribution is an algorithm based on acceleration, which converges at optimal speed, both from the optimization point of view and from the statistical one. In the non-parametric setting, this can improve the convergence rate up to optimality, even inparticular regimes for which the first algorithm remains sub-optimal. Finally, the third contribution of the thesis consists in an extension of the framework beyond the least-square loss. The stochastic gradient descent algorithm is analyzed as a Markov chain. This point of view leads to an intuitive and insightful interpretation, that outlines the differences between the quadratic setting and the more general setting. A simple method resulting in provable improvements in the convergence is then proposed.

Dans cette thèse, nous considérons le modèle de régression avec plusieurs unités expérimentales, où les erreurs forment un processus d'autocovariance dans un cadre générale, c'est-à-dire, un processus du second ordre (stationnaire ou non stationnaire) avec une autocovariance non différentiable le long de la diagonale. Nous sommes intéressés, entre autres, à l'estimation non paramétrique de la fonction de régression de ce modèle.Premièrement, nous considérons l'estimateur classique proposé par Gasser et Müller. Nous étudions ses performances asymptotiques quand le nombre d'unités expérimentales et le nombre d'observations tendent vers l'infini. Pour un échantillonnage régulier, nous améliorons les vitesses de convergence d'ordre supérieur de son biais et de sa variance. Nous montrons aussi sa normalité asymptotique dans le cas des erreurs corrélées.Deuxièmement, nous proposons un nouvel estimateur à noyau pour la fonction de régression, basé sur une propriété de projection. Cet estimateur est construit à travers la fonction d'autocovariance des erreurs et une fonction particulière appartenant à l'Espace de Hilbert à Noyau Autoreproduisant (RKHS) associé à la fonction d'autocovariance. Nous étudions les performances asymptotiques de l'estimateur en utilisant les propriétés de RKHS. Ces propriétés nous permettent d'obtenir la vitesse optimale de convergence de la variance de cet estimateur. Nous prouvons sa normalité asymptotique, et montrons que sa variance est asymptotiquement plus petite que celle de l'estimateur de Gasser et Müller. Nous conduisons une étude de simulation pour confirmer nos résultats théoriques.Troisièmement, nous proposons un nouvel estimateur à noyau pour la fonction de régression. Cet estimateur est construit en utilisant la règle numérique des trapèzes, pour approximer l'estimateur basé sur des données continues. Nous étudions aussi sa performance asymptotique et nous montrons sa normalité asymptotique. En outre, cet estimateur permet d'obtenir le plan d'échantillonnage optimal pour l'estimation de la fonction de régression. Une étude de simulation est conduite afin de tester le comportement de cet estimateur dans un plan d'échantillonnage de taille finie, en terme d'erreur en moyenne quadratique intégrée (IMSE). De plus, nous montrons la réduction dans l'IMSE en utilisant le plan d'échantillonnage optimal au lieu de l'échantillonnage uniforme.Finalement, nous considérons une application de la régression non paramétrique dans le domaine pharmacocinétique. Nous proposons l'utilisation de l'estimateur non paramétrique à noyau pour l'estimation de la fonction de concentration. Nous vérifions son bon comportement par des simulations et une analyse de données réelles. Nous investiguons aussi le problème de l'estimation de l'Aire Sous la Courbe de concentration (AUC), pour lequel nous proposons un nouvel estimateur à noyau, obtenu par l'intégration de l'estimateur à noyau de la fonction de régression. Nous montrons, par une étude de simulation, que le nouvel estimateur est meilleur que l'estimateur classique en terme d'erreur en moyenne quadratique. Le problème crucial de l'obtention d'un plan d'échantillonnage optimale pour l'estimation de l'AUC est discuté en utilisant l'algorithme de recuit simulé généralisé. / In this thesis, we consider the fixed design regression model with repeated measurements, where the errors form a process with general autocovariance function, i.e. a second order process (stationary or nonstationary), with a non-differentiable covariance function along the diagonal. We are interested, among other problems, in the nonparametric estimation of the regression function of this model.We first consider the well-known kernel regression estimator proposed by Gasser and Müller. We study its asymptotic performance when the number of experimental units and the number of observations tend to infinity. For a regular sequence of designs, we improve the higher rates of convergence of the variance and the bias. We also prove the asymptotic normality of this estimator in the case of correlated errors.Second, we propose a new kernel estimator of the regression function based on a projection property. This estimator is constructed through the autocovariance function of the errors, and a specific function belonging to the Reproducing Kernel Hilbert Space (RKHS) associated to the autocovariance function. We study its asymptotic performance using the RKHS properties. These properties allow to obtain the optimal convergence rate of the variance. We also prove its asymptotic normality. We show that this new estimator has a smaller asymptotic variance then the one of Gasser and Müller. A simulation study is conducted to confirm this theoretical result.Third, we propose a new kernel estimator for the regression function. This estimator is constructed through the trapezoidal numerical approximation of the kernel regression estimator based on continuous observations. We study its asymptotic performance, and we prove its asymptotic normality. Moreover, this estimator allow to obtain the asymptotic optimal sampling design for the estimation of the regression function. We run a simulation study to test the performance of the proposed estimator in a finite sample set, where we see its good performance, in terms of Integrated Mean Squared Error (IMSE). In addition, we show the reduction of the IMSE using the optimal sampling design instead of the uniform design in a finite sample set.Finally, we consider an application of the regression function estimation in pharmacokinetics problems. We propose to use the nonparametric kernel methods, for the concentration-time curve estimation, instead of the classical parametric ones. We prove its good performance via simulation study and real data analysis. We also investigate the problem of estimating the Area Under the concentration Curve (AUC), where we introduce a new kernel estimator, obtained by the integration of the regression function estimator. We prove, using a simulation study, that the proposed estimators outperform the classical one in terms of Mean Squared Error. The crucial problem of finding the optimal sampling design for the AUC estimation is investigated using the Generalized Simulating Annealing algorithm.

Filtering for Stochastic Evolution Equations Vít Kubelka Doctoral thesis Abstract Linear filtering problem for infinite-dimensional Gaussian processes is studied, the observation process being finite-dimensional. Integral equations for the filter and for covariance of the error are derived. General results are applied to linear SPDEs driven by Gauss-Volterra process observed at finitely many points of the domain and to delayed SPDEs driven by white noise. Subsequently, the continuous dependence of the filter and observation error on parameters which may be present both in the signal and the obser- vation process is proved. These results are applied to signals governed by stochastic heat equations driven by distributed or pointwise fractional noise. The observation process may be a noisy observation of the signal at given points in the domain, the position of which may depend on the parameter. 1

We focus on the Tensor Product Structure (TPS) of the Hilbert space and the fact that a choice in the TPS has an impact on the representation of the studied quantum system. We define the measurement problem in quantum mechanics and present some theories about quantum mechanics, each of them highlighting a different approach to quantum measurements. Then, a new approach to quantum measurement is presented by considering it as a change in the Tensor Product Structure of the Hilbert space associated with the description of a system. The system is made of a physical quantum system entangled with a measurement device. The description of the system changes to a new one where there is no entanglement anymore between the physical system and the measurement apparatus. The change in the TPS is performed using a global unitary transformation and more precisely by diagonalizing the density matrix of the system using unitary matrices. Four sets of matrices are obtained, each of them diagonalizing the density matrix in a different way for our toy model made of 2 qubits. Then, we want to recover Born’s rule directly from the diagonalizing matrices by measuring the size of their sets using Haar measure. We have not been able to conclude this program, but we outline what is expected to happen such that standard probabilities can be recovered.

Cette thèse se concentrera exclusivement sur l’application de méthodes non paramétriques basées sur le noyau à des problèmes d’identification non-linéaires. Comme pour les autres méthodes non-linéaires, deux questions clés dans l’identification basée sur le noyau sont les questions de comment définir un modèle non-linéaire (sélection du noyau) et comment ajuster la complexité du modèle (régularisation). La contribution principale de cette thèse est la présentation et l’étude de deux critères d’optimisation (un existant dans la littérature et une nouvelle proposition) pour l’approximation structurale et l’accord de complexité dans l’identification de systèmes non-linéaires basés sur le noyau. Les deux méthodes sont basées sur l’idée d’intégrer des contraintes de complexité basées sur des caractéristiques dans le critère d’optimisation, en pénalisant les dérivées de fonctions. Essentiellement, de telles méthodes offrent à l’utilisateur une certaine souplesse dans la définition d’une fonction noyau et dans le choix du terme de régularisation, ce qui ouvre de nouvelles possibilités quant à la facon dont les modèles non-linéaires peuvent être estimés dans la pratique. Les deux méthodes ont des liens étroits avec d’autres méthodes de la littérature, qui seront examinées en détail dans les chapitres 2 et 3 et formeront la base des développements ultérieurs de la thèse. Alors que l’analogie sera faite avec des cadres parallèles, la discussion sera ancrée dans le cadre de Reproducing Kernel Hilbert Spaces (RKHS). L’utilisation des méthodes RKHS permettra d’analyser les méthodes présentées d’un point de vue à la fois théorique et pratique. De plus, les méthodes développées seront appliquées à plusieurs «études de cas» d’identification, comprenant à la fois des exemples de simulation et de données réelles, notamment : • Détection structurelle dans les systèmes statiques non-linéaires. • Contrôle de la fluidité dans les modèles LPV. • Ajustement de la complexité à l’aide de pénalités structurelles dans les systèmes NARX. • Modelisation de trafic internet par l’utilisation des méthodes à noyau / This thesis will focus exclusively on the application of kernel-based nonparametric methods to nonlinear identification problems. As for other nonlinear methods, two key questions in kernel-based identification are the questions of how to define a nonlinear model (kernel selection) and how to tune the complexity of the model (regularisation). The following chapter will discuss how these questions are usually dealt with in the literature. The principal contribution of this thesis is the presentation and investigation of two optimisation criteria (one existing in the literature and one novel proposition) for structural approximation and complexity tuning in kernel-based nonlinear system identification. Both methods are based on the idea of incorporating feature-based complexity constraints into the optimisation criterion, by penalising derivatives of functions. Essentially, such methods offer the user flexibility in the definition of a kernel function and the choice of regularisation term, which opens new possibilities with respect to how nonlinear models can be estimated in practice. Both methods bear strong links with other methods from the literature, which will be examined in detail in Chapters 2 and 3 and will form the basis of the subsequent developments of the thesis. Whilst analogy will be made with parallel frameworks, the discussion will be rooted in the framework of Reproducing Kernel Hilbert Spaces (RKHS). Using RKHS methods will allow analysis of the methods presented from both a theoretical and a practical point-of-view. Furthermore, the methods developed will be applied to several identification ‘case studies’, comprising of both simulation and real-data examples, notably: • Structural detection in static nonlinear systems. • Controlling smoothness in LPV models. • Complexity tuning using structural penalties in NARX systems. • Internet traffic modelling using kernel methods

In this paper we deal with the `strength' of ill-posedness for ill-posed linear operator equations Ax = y in Hilbert spaces, where we distinguish according_to_M. Z. Nashed [15] the ill-posedness of type I if A is not compact, but we have R(A) 6= R(A) for the range R(A) of A; and the ill-posedness of type II for compact operators A: From our considerations it seems to follow that the problems with noncompact operators A are not in general `less' ill-posed than the problems with compact operators. We motivate this statement by comparing the approximation and stability behaviour of discrete least-squares solutions and the growth rate of Galerkin matrices in both cases. Ill-posedness measures for compact operators A as discussed in [10] are derived from the decay rate of the nonincreasing sequence of singular values of A. Since singular values do not exist for noncompact operators A; we introduce stability rates in order to have a common measure for the compact and noncompact cases. Properties of these rates are illustrated by means of convolution equations in the compact case and by means of equations with multiplication operators in the noncompact case. Moreover using increasing rearrangements of the multiplier functions specific measures of ill-posedness called ill-posedness rates are considered for the multiplication operators. In this context, the character of sufficient conditions providing convergence rates of Tikhonov regularization are compared for compact operators and multiplication operators.

No description available.

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES / In this work, we are treated some elements of functional analysis such as Banach spaces, inner product spaces and Hilbert spaces, also studied Fourier series and at the end briefly consider the equation of the vibrating string. With this, you realize that you do not need a lot of theory in order to get significant results. / Neste trabalho, são tratados alguns elementos da análise funcional como espaços de Banach, espaços com produto interno e espaços de Hilbert, estudamos também séries de Fourier e no final consideramos brevemente a equação da corda vibrante. Com isso, percebe-se que não se precisa de muita teoria para conseguirmos resultados significativos.

Made available in DSpace on 2016-08-17T14:53:18Z (GMT). No. of bitstreams: 1 Dissertacao Ewaldo.pdf: 1169300 bytes, checksum: fc5d4b9840bbafe39d03cd1221da615e (MD5) Previous issue date: 2012-02-10 / This work derives and evaluates a nonlinear method for Blind Source Extraction (BSE) in a Reproducing Kernel Hilbert Space (RKHS) framework. For extracting the desired signal from a mixture a priori information about the autocorrelation function of that signal translated in a linear transformation of the Gram matrix of the nonlinearly transformed data to the Hilbert space. Our method proved to be more robust than methods presented in the literature of BSE with respect to ambiguities in the available a priori information of the signal to be extracted. The approach here introduced can also be seen as a generalization of Kernel Principal Component Analysis to analyze autocorrelation matrices at specific time lags. Henceforth, the method here presented is a kernelization of Dependent Component Analysis, it will be called Kernel Dependent Component Analysis (KDCA). Also in this dissertation it will be show a Information-Theoretic Learning perspective of the analysis, this will study the transformations in the extracted signals probability density functions while linear operations calculated in the RKHS. / Esta dissertação deriva e avalia um novo método nãolinear para Extração Cega de Sinais através de operações algébricas em um Espaço de Hilbert Reproduzido por Kernel (RKHS, do inglês Reproducing Kernel Hilbert Space). O processo de extração de sinais desejados de misturas é realizado utilizando-se informação sobre a estrutura temporal deste sinal desejado. No presente trabalho, esta informação temporal será utilizada para realizar uma transformação linear na matriz de Gram das misturas transformadas para o espaço de Hilbert. Aqui, mostrarse- á também que o método proposto é mais robusto, com relação a ambigüidades sobre a informação temporal do sinal desejado, que aqueles previamente apresentados na literatura para realizar a mesma operação de extração. A abordagem estudada a seguir pode ser vista como uma generalização da Análise de Componentes Principais utilizando Kerneis para analisar matriz de autocorrelação dos dados para um atraso específico. Sendo também uma kernelização da Análise de Componentes Dependentes, o método aqui desenvolvido é denominado Análise de Componentes Dependentes utilizando Kerneis (KDCA, do inglês Kernel Dependent Component Analysis). Também será abordada nesta dissertação, a perspectiva da Aprendizagem de Máquina utilizando Teoria da Informação do novo método apresentado, mostrando assim, que transformações são realizadas na função densidade de probabilidade do sinal extraído enquanto que operação lineares são calculadas no RKHS.