Sequential Machine learning Approaches for Portfolio Management

Cette thèse envisage un ensemble de méthodes permettant aux algorithmes d'apprentissage statistique de mieux traiter la nature séquentielle des problèmes de gestion de portefeuilles financiers. Nous débutons par une considération du problème général de la composition d'algorithmes d'apprentissage devant gérer des tâches séquentielles, en particulier celui de la mise-à-jour efficace des ensembles d'apprentissage dans un cadre de validation séquentielle. Nous énumérons les desiderata que des primitives de composition doivent satisfaire, et faisons ressortir la difficulté de les atteindre de façon rigoureuse et efficace. Nous poursuivons en présentant un ensemble d'algorithmes qui atteignent ces objectifs et présentons une étude de cas d'un système complexe de prise de décision financière utilisant ces techniques. Nous décrivons ensuite une méthode générale permettant de transformer un problème de décision séquentielle non-Markovien en un problème d'apprentissage supervisé en employant un algorithme de recherche basé sur les K meilleurs chemins. Nous traitons d'une application en gestion de portefeuille où nous entraînons un algorithme d'apprentissage à optimiser directement un ratio de Sharpe (ou autre critère non-additif incorporant une aversion au risque). Nous illustrons l'approche par une étude expérimentale approfondie, proposant une architecture de réseaux de neurones spécialisée à la gestion de portefeuille et la comparant à plusieurs alternatives. Finalement, nous introduisons une représentation fonctionnelle de séries chronologiques permettant à des prévisions d'être effectuées sur un horizon variable, tout en utilisant un ensemble informationnel révélé de manière progressive. L'approche est basée sur l'utilisation des processus Gaussiens, lesquels fournissent une matrice de covariance complète entre tous les points pour lesquels une prévision est demandée. Cette information est utilisée à bon escient par un algorithme qui transige activement des écarts de cours (price spreads) entre des contrats à terme sur commodités. L'approche proposée produit, hors échantillon, un rendement ajusté pour le risque significatif, après frais de transactions, sur un portefeuille de 30 actifs.

A dynamic sequential route choice model for micro-simulation

Dans les études sur le transport, les modèles de choix de route décrivent la sélection par un utilisateur d’un chemin, depuis son origine jusqu’à sa destination. Plus précisément, il s’agit de trouver dans un réseau composé d’arcs et de sommets la suite d’arcs reliant deux sommets, suivant des critères donnés. Nous considérons dans le présent travail l’application de la programmation dynamique pour représenter le processus de choix, en considérant le choix d’un chemin comme une séquence de choix d’arcs. De plus, nous mettons en œuvre les techniques d’approximation en programmation dynamique afin de représenter la connaissance imparfaite de l’état réseau, en particulier pour les arcs éloignés du point actuel. Plus précisément, à chaque fois qu’un utilisateur atteint une intersection, il considère l’utilité d’un certain nombre d’arcs futurs, puis une estimation est faite pour le restant du chemin jusqu’à la destination. Le modèle de choix de route est implanté dans le cadre d’un modèle de simulation de trafic par événements discrets. Le modèle ainsi construit est testé sur un modèle de réseau routier réel afin d’étudier sa performance.

Welfare criteria from choice: the sequential solution

We study the problem of deriving a complete welfare ordering from a choice function. Under the sequential solution, the best alternative is the alternative chosen from the universal set; the second best is the one chosen when the best alternative is removed; and so on. We show that this is the only completion of Bernheim and Rangel's (2009) welfare relation that satisfies two natural axioms: neutrality, which ensures that the names of the alternatives are welfare-irrelevant; and persistence, which stipulates that every choice function between two welfare-identical choice functions must exhibit the same welfare ordering.

Preparation of sub-micrometre thick CulnSe2 films using sequential evaporation technique for device fabrication

In this work. Sub-micrometre thick CulnSe2 films were prepared using different techniques viz, selenization through chemically deposited Selenium and Sequential Elemental Evaporation. These methods are simpler than co-evaporation technique, which is known to be the most suitable one for CulnSe2 preparation. The films were optimized by varying the composition over a wide range to find optimum properties for device fabrication. Typical absorber layer thickness of today's solar cell ranges from 2-3m. Thinning of the absorber layer is one of the challenges to reduce the processing time and material usage, particularly of Indium. Here we made an attempt to fabricate solar cell with absorber layer of thickness

Sequential interactions of Silver-silica nanocomposite (Ag-SiO2NC) with cell wall, metabolism and genetic stability of Psedomonas aeruginosa, a multiple antibiotic resistant bacterium

The study was carried out to understand the effect of silver-silica nanocomposite (Ag-SiO2NC) on the cell wall integrity, metabolism and genetic stability of Pseudomonas aeruginosa, a multiple drugresistant bacterium. Bacterial sensitivity towards antibiotics and Ag-SiO2NC was studied using standard disc diffusion and death rate assay, respectively. The effect of Ag-SiO2NC on cell wall integrity was monitored using SDS assay and fatty acid profile analysis while the effect on metabolism and genetic stability was assayed microscopically, using CTC viability staining and comet assay, respectively. P. aeruginosa was found to be resistant to β-lactamase, glycopeptidase, sulfonamide, quinolones, nitrofurantoin and macrolides classes of antibiotics. Complete mortality of the bacterium was achieved with 80 μgml-1 concentration of Ag-SiO2NC. The cell wall integrity reduced with increasing time and reached a plateau of 70 % in 110 min. Changes were also noticed in the proportion of fatty acids after the treatment. Inside the cytoplasm, a complete inhibition of electron transport system was achieved with 100 μgml-1 Ag-SiO2NC, followed by DNA breakage. The study thus demonstrates that Ag-SiO2NC invades the cytoplasm of the multiple drug-resistant P. aeruginosa by impinging upon the cell wall integrity and kills the cells by interfering with electron transport chain and the genetic stability

Contact Sensing: A Sequential Decision Approach to Sensing Manipulation Contact

This paper describes a new statistical, model-based approach to building a contact state observer. The observer uses measurements of the contact force and position, and prior information about the task encoded in a graph, to determine the current location of the robot in the task configuration space. Each node represents what the measurements will look like in a small region of configuration space by storing a predictive, statistical, measurement model. This approach assumes that the measurements are statistically block independent conditioned on knowledge of the model, which is a fairly good model of the actual process. Arcs in the graph represent possible transitions between models. Beam Viterbi search is used to match measurement history against possible paths through the model graph in order to estimate the most likely path for the robot. The resulting approach provides a new decision process that can be use as an observer for event driven manipulation programming. The decision procedure is significantly more robust than simple threshold decisions because the measurement history is used to make decisions. The approach can be used to enhance the capabilities of autonomous assembly machines and in quality control applications.

Sequential Optimal Recovery: A Paradigm for Active Learning

In most classical frameworks for learning from examples, it is assumed that examples are randomly drawn and presented to the learner. In this paper, we consider the possibility of a more active learner who is allowed to choose his/her own examples. Our investigations are carried out in a function approximation setting. In particular, using arguments from optimal recovery (Micchelli and Rivlin, 1976), we develop an adaptive sampling strategy (equivalent to adaptive approximation) for arbitrary approximation schemes. We provide a general formulation of the problem and show how it can be regarded as sequential optimal recovery. We demonstrate the application of this general formulation to two special cases of functions on the real line 1) monotonically increasing functions and 2) functions with bounded derivative. An extensive investigation of the sample complexity of approximating these functions is conducted yielding both theoretical and empirical results on test functions. Our theoretical results (stated insPAC-style), along with the simulations demonstrate the superiority of our active scheme over both passive learning as well as classical optimal recovery. The analysis of active function approximation is conducted in a worst-case setting, in contrast with other Bayesian paradigms obtained from optimal design (Mackay, 1992).

Why peace processes fail or move forward? Negotiations in Colombia with FARC and AUC (1998-2003)

Este trabajo examina la teoría sobre guerras civiles y resolución de conflictos con el fin de contestar la pregunta: ¿por qué fracasan o progresan los procesos de paz? Se miraron los procesos de paz en Colombia en los últimos cinco años cuando comenzó y fracasó el proceso de paz con las Fuerzas Armadas Revolucionarias de Colombia, FARC y comenzaron con las Autodefensas Unidas de Colombia, AUC. La teoría revela la relevancia de factores económicos, políticos, participación externa y militares para explicar por que fallan o prosperan los procesos de paz. Por su parte, el fracaso de las negociaciones con las FARC puede explicarse por razones de estrategia militar, el rol de la violencia durante la negociación y la falta de participación internacional. De otro lado, evitando todos los puntos sensibles de la negociación inicial, las AUC ganaron apoyo de la opinión publica y la confianza del gobierno para iniciar los diálogos. De esta forma, tenemos dos procesos recientes en Colombia para analizar: uno que fallo y el otro que esta progresando. El análisis de estos procesos puede ayudarnos a contestar la pregunta inicial de este trabajo.

Syllable-frequency effect in visual word recognition : evidence or sequential-type processing. 'El efecto de frecuencia silábica en el reconcimiento visual de palabras : evidencia de un proceso secuencial tipo'.

Resumen tomado de la revista

Energy on the move : un aula sin fronteras.

Resumen tomado de la publicación

Edexcel A2 Unit 4 Physics : physics on the move.

Guía de apoyo para alumnos de educación secundaria de segundo ciclo que sigan la especificación de Edexcel en el nivel A2 del área de física. Está estructurada en tres secciones: una introducción con una breve explicación de los enfoques y técnicas a utilizar para contestar correctamente las preguntas del examen; una guía de contenidos con los conceptos y temas básicos (mecánica, campos eléctricos y magnéticos, física de partículas) acompañados de ejemplos para explicar la teoría e ilustrar los ejercicios que pueden aparecer en la prueba oficial; y una sección con dos ejemplos de examen y dos juegos de respuestas para cada uno comentadas por un examinador.

An analysis of the move to Inclusive Education in Canada : what works

Incluye anexo

Formação e supervisão : o que move os professores?

A finalidade deste estudo é identificar que professores frequentam o Curso de Mestrado em Ciências da Educação, com especialização em Supervisão. Interessa determinar o perfil desses professores, averiguar as suas percepções da supervisão, verificar o que os motiva a investirem na formação contínua e no desenvolvimento profissional e quais são os seus interesses, ao iniciar um segundo ciclo de estudos. Em contexto de formação especializada, foi concretizado um estudo de caso numa Universidade Portuguesa, com aplicação de metodologia mista, qualitativa e quantitativa. Os resultados mostram que os professores mais motivados, convencidos da utilidade do seu trabalho, procuram, na concretização de um segundo ciclo de estudos no Ensino Superior, uma jornada de desenvolvimento pessoal e profissional. Interessa-lhes o aperfeiçoamento da praxis em interligação com theoretical inputs, através de uma reflexão estruturada, actualização científico-pedagógica, investigação em acção e consequente melhoria das práticas. O estudo evidencia o imperativo da formação docente para uma supervisão formativa e democrática, enquanto factor de mudança do processo educativo e da escola, entendida como comunidade supervisiva aprendente.

History does not move in a straight line. CEPS Commentary, 5 July 2012

Eight years have passed since the EU launched its European Neighbourhood Policy, aimed at inducing its neighbours to the east to converge on modern European values and economic norms. In this Commentary, Michael Emerson reflects on the curious and circuitous turn of events in the region during this period. Michael Emerson is Senior Associate Research Fellow at CEPS.