Minimum Divergence Methods in Statistical Machine Learning : From an Information Geometric Viewpoint

Idioma: inglés

Editorial: Springer, Springer, 2022

4431569200 / 9784431569206

Librería: AHA-BUCH GmbH, Einbeck, AlemaniaAHA-BUCH GmbH

Vendedor de 5 estrellas

Vendedor de AbeBooks desde 14 de agosto de 2006

Ver los artículos de este vendedor
Tapa dura

Condición: Nuevo

EUR 168,73

Envío por EUR 62,59 
Se envía de Alemania a Estados Unidos de America

Cantidad disponible: 1 disponibles

Añadir al carrito

Descripción del artículo del vendedor

Druck auf Anfrage Neuware - Printed after ordering - This book explores minimum divergence methods of statistical machine learning for estimation, regression, prediction, and so forth, in which we engage in information geometry to elucidate their intrinsic properties of the corresponding loss functions, learning algorithms, and statistical models.One of the most elementary examples is Gauss's least squares estimator in a linear regression model, in which the estimator is given by minimization of the sum of squares between a response vector and a vector of the linear subspace hulled by explanatory vectors. This is extended to Fisher's maximum likelihood estimator (MLE) for an exponential model, in which the estimator is provided by minimization of the Kullback-Leibler (KL) divergence between a data distribution and a parametric distribution of the exponential model in an empirical analogue. Thus, we envisage a geometric interpretation of such minimization procedures such that a right triangle is kept with Pythagorean identity in the sense of the KL divergence. This understanding sublimates a dualistic interplay between a statistical estimation and model, which requires dual geodesic paths, called m-geodesic and e-geodesic paths, in a framework of information geometry. We extend such a dualistic structure of the MLE and exponential model to that of the minimum divergence estimator and the maximum entropy model, which is applied to robust statistics, maximum entropy, density estimation, principal component analysis, independent component analysis, regression analysis, manifold learning, boosting algorithm, clustering, dynamic treatment regimes, and so forth. We consider a variety of information divergence measures typically including KL divergence to express departure from one probability distribution to another. An information divergence is decomposed into the cross-entropy and the (diagonal) entropy in which the entropy associates with a generative model as a family of maximum entropy distributions; the cross entropy associates with a statistical estimation method via minimization of the empirical analogue based on given data. Thus any statistical divergence includes an intrinsic object between the generative model and the estimation method. Typically, KL divergence leads to the exponential model and the maximum likelihood estimation. It is shown that any information divergence leads to a Riemannian metric and a pair of the linear connections in the framework of information geometry. We focus on a class of information divergence generated by an increasing and convex function U, called U-divergence. It is shown that any generator function U generates the U-entropy and U-divergence, in which there is a dualistic structure between the U-divergence method and the maximum U-entropy model. We observe that a specific choice of U leads to a robust statistical procedurevia the minimum U-divergence method. If U is selected as an exponential function, then the corresponding U-entropy and U-divergence are reduced to the Boltzmann-Shanon entropy and the KL divergence; the minimum U-divergence estimator is equivalent to the MLE. For robust supervised learning to predict a class label we observe that the U-boosting algorithm performs well for contamination of mislabel examples if U is appropriately selected. We present such maximal U-entropy and minimum U-divergence methods, in particular, selecting a power function as U to provide flexible performance in statistical machine learning.

N° de ref. del artículo 9784431569206

Título
Minimum Divergence Methods in Statistical Machine Learning : From an Information Geometric Viewpoint
Autor
Shinto Eguchi
Editorial
Springer, Springer
Año de publicación
2022
Estado
Neu
Encuadernación
Buch
Idioma
inglés
ISBN 10
4431569200
ISBN 13
9784431569206
Peso del artículo
518 gramos
Dimensiones
241x160x19 mm

AHA-BUCH GmbH

Einbeck, Alemania

Vendedor de 5 estrellas

Vendedor de AbeBooks desde 14 de agosto de 2006

Tarifas de envío de Alemania a Estados Unidos de America

ArtículoDe 30 a 40 días hábilesDe 7 a 14 días hábiles
Primer artículoEUR 62,59EUR 72,59
Los plazos de entrega los establecen los vendedores y varían según el transportista y la ubicación. Los pedidos que pasan por la aduana pueden sufrir retrasos y los compradores son responsables de los aranceles o tarifas asociadas. Los vendedores pueden ponerse en contacto con usted en relación con cargos adicionales para cubrir cualquier aumento en los costes de envío de los artículos.

Métodos de pago

  • Visa
  • Mastercard
  • American Express
  • Carte Bleue
  • Apple Pay
  • Google Pay
  • Cheque
  • Giro bancario
  • PayPal

Descripción de la tienda

Das Unternehmen AHA-BUCH GmbH: Seit der Gründung von AHA-BUCH im Juli 2005 ist unser Hauptziel, zufriedenen Kunden so schnell und so preisgünstig wie möglich ihren Bücherwunsch zu erfüllen. Unsere Firma beschäftigt 16 Mitarbeiter, die nur ein Ziel kennen: den Kunden und seine Wünsche! Auf über 3700 m2 Fläche haben wir über 100.000 Bücher, Modernes Antiquariat und Spiele auf Lager.

Especialidad

Kinderbücher & Kinderhör Casetten, German Books, Software, Natur & Tiere, Ratgeber, Sachbücher, Englische Bücher, Medizin & Gesundheit, Universität & Studium

Información empresarial del vendedor

AHA-BUCH GmbH

Garlebsen 48
Einbeck, Alemania 37574