Loi de probabilité à plusieurs variables

Résumé

vignette|Représentation d'une loi normale multivariée. Les courbes rouge et bleue représentent les lois marginales. Les points noirs sont des réalisations de cette distribution à plusieurs variables. Dans certains problèmes interviennent simultanément plusieurs variables aléatoires. Mis à part les cas particuliers de variables indépendantes (notion définie ci-dessous) et de variables liées fonctionnellement, cela introduit la notion de loi de probabilité à plusieurs variables autrement appelée loi jointe. La description des notions correspondantes, certaines d'entre elles généralisant les notions relatives à une seule variable, est simplifiée de deux manières :

Seules les variables continues sont considérées. Il est possible de passer aux variables discrètes en utilisant la fonction de Heaviside et la fonction de Dirac.
Pour éviter la lourdeur des formules, l'exposé est limité à deux variables.

Formules de base La probabilité pour que la variable aléatoire X,

Source officielle

https://fr.wikipedia.org/wiki/Loi_de_probabilit%C3%A9_%C3%A0_plusieurs_variables

À propos de ce résultat

Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.

Publications associées (37)

Publications associées

Chargement

Personnes associées (2)

Personnes associées

Chargement

Unités associées (3)

Unités associées

Chargement

Concepts associés (39)

Concepts associés

Chargement

Cours associés (62)

Cours associés

Chargement

Séances de cours associées (196)

Séances de cours associées

Chargement

Learning Search Strategies from Human Demonstrations

Guillaume Pierre Luc De Chambrier

Decision making and planning with partial state information is a problem faced by all forms of intelligent entities. The formulation of a problem under partial state information leads to an exorbitant set of choices with associated probabilistic outcomes making its resolution difficult when using traditional planning methods. Human beings have acquired the ability of acting under uncertainty through education and self-learning. Transferring our know-how to artificial agents and robots will make it faster for them to learn and even improve upon us in tasks in which incomplete knowledge is available, which is the objective of this thesis. We model how humans reason with respect to their beliefs and transfer this knowledge in the form of a parameterised policy, following a Programming by Demonstration framework, to a robot apprentice for two spatial navigation tasks: the first task consists of localising a wooden block on a table and for the second task a power socket must be found and connected. In both tasks the human teacher and robot apprentice only rely on haptic and tactile information. We model the human and robot's beliefs by a probability density function which we update through recursive Bayesian state space estimation. To model the reasoning processes of human subjects performing the search tasks we learn a generative joint distribution over beliefs and actions (end-effector velocities) which were recorded during the executions of the task. For the first search task the direct mapping from belief to actions is learned whilst for the second task we incorporate a cost function used to adapt the policy parameters in a Reinforcement Learning framework and show a considerable improvement over solely learning the behaviour with respect to the distance taken to accomplish the task. Both search tasks above can be considered as active localisation as the uncertainty originates only from the position of the agent in the world. We consider searches in which both the position of the robot and features of the environment are uncertain. Given the unstructured nature of the belief a histogram parametrisation of the joint distribution of the robots position and features is necessary. However, naively doing so becomes quickly intractable as the space and time complexity is exponential. We demonstrate that by only parametrising the marginals and by memorising the parameters of the measurement likelihood functions we can recover the exact same solution as the naive parametrisations at a cost which is linear in space and time complexity.

EPFL2016

Chargement

Since the 2008 Global Financial Crisis, the financial market has become more unpredictable than ever before, and it seems set to remain so in the forseeable future. This means an investor faces unprecedented risks, hence the increasing need for robust portfolio optimization to protect them against uncertainty, which is potentially devastating if unattended yet ignored in the classical Markowitz model, whose another deficiency is the absence of higher moments in its assumption of the distribution of asset returns. We establish an equivalence between the Markowitz model and the portfolio return value-at-risk optimization problem under multivariate normality of asset returns, so that we can add these excluded features into the former implicitly by incorporating them into the latter. We also provide a probabilistic smoothing spline approximation method and a deterministic model within the location-scale framework under elliptical distribution of the asset returns to solve the robust portfolio return value-at-risk optimization problem. In particular for the deterministic model, we introduce a novel eigendecomposition uncertainty set which lives in the positive definite space for the scale matrix without compromising on the computational complexity and conservativeness of the optimization problem, invent a method to determine the size of the involved uncertainty sets, test it out on real data, and explore its diversification properties. Although the value-at-risk has been the standard risk measure adopted by the banking and insurance industry since the early nineties, it has since attracted many criticisms, in particular from McNeil et al. (2005) and the Basel Committee on Banking Supervision in 2012, also known as Basel 3.5. Basel 4 even suggests a move away from the what" value-at-risk to the what-if" conditional value-at-risk' measure. We shall see that the former may be replaced with the latter or even other risk measures in our formulations easily.

EPFL2017

Chargement

Gaussian distribution for the divisor function and Hecke eigenvalues in arithmetic progressions

Philippe Michel

We show that, in a restricted range, the divisor function of integers in residue classes modulo a prime follows a Gaussian distribution, and a similar result for Hecke eigenvalues of classical holomorphic cusp forms. Furthermore, we obtain the joint distribution of these arithmetic functions in two related residue classes. These results follow from asymptotic evaluations of the relevant moments, and depend crucially on results on the independence of monodromy groups related to products of Kloosterman sums.

European Mathematical Soc2014

Chargement

Learning Search Strategies from Human Demonstrations

Guillaume Pierre Luc De Chambrier

EPFL2016