Mathematical Theories Of Machine Learning - Theory And Applications

26 juin 2019|
Mathematical Theories Of Machine Learning - Theory And Applications de Bin Shi
152,95 $
Couverture rigide
Obtenez 765 points privilègeᴹᴰ
Acheter en ligne
Livraison à une adresse
Expédition gratuite pour les commandes d’au moins 35 $
Cueillette en magasin
Pour savoir si la cueillette en magasin est offerte,
Trouver en magasin
Non vendu en magasin
Les prix et les offres peuvent différer de ceux en magasin


This book studies mathematical theories of machine learning. The first part of the book explores the optimality and adaptivity of choosing step sizes of gradient descent for escaping strict saddle points in non-convex optimization problems. In the second part, the authors propose algorithms to find local minima in nonconvex optimization and to obtain global minima in some degree from the Newton Second Law without friction. In the third part, the authors study the problem of subspace clustering with noisy and missing data, which is a problem well-motivated by practical applications data subject to stochastic Gaussian noise and/or incomplete data with uniformly missing entries. In the last part, the authors introduce an novel VAR model with Elastic-Net regularization and its equivalent Bayesian model allowing for both a stable sparsity and a group selection. 

Bin Shi is a Ph.D. candidate in the School of Computing and Information Sciences at FIU under the supervision of Professor Sitharama S. Iyengar. His preliminary research focuses on the theory of machine learning, especially on optimization. Bin Shi received his B.S. of Applied Math from Ocean University of China, China in 2006, Master ...
Titre :Mathematical Theories Of Machine Learning - Theory And Applications
Format :Couverture rigide
Dimensions de l'article :133 pages, 9.25 X 6.1 X 1 po
Dimensions à l'expédition :133 pages, 9.25 X 6.1 X 1 po
Publié le :26 juin 2019
Publié par :Springer Nature
Langue :anglais
Convient aux âges :Tous les âges
ISBN - 13 :9783030170752

Consulté récemment