A randomized algorithm for the exact solution of transductive support vector machines

Random sampling is an efficient method for dealing with constrained optimization problems. In computational geometry, this method has been successfully applied, through Clarkson’s algorithm (Clarkson 1996), to solve a general class of problems called violator spaces. In machine learning, Transductiv...

Descripción completa

Detalles Bibliográficos
Autores: Esposito, Gennaro|||0000-0002-9700-2971, Martín Muñoz, Mario|||0000-0002-4125-6630
Tipo de recurso: artículo
Fecha de publicación:2015
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/83017
Acceso en línea:https://hdl.handle.net/2117/83017
https://dx.doi.org/10.1080/08839514.2015.1035951
Access Level:acceso abierto
Palabra clave:Supervised learning (Machine learning)
Semisupervised Learning
Transduction Support Vector Machine
Classification
Aprenentatge automàtic
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
Descripción
Sumario:Random sampling is an efficient method for dealing with constrained optimization problems. In computational geometry, this method has been successfully applied, through Clarkson’s algorithm (Clarkson 1996), to solve a general class of problems called violator spaces. In machine learning, Transductive Support Vector Machines (TSVM) is a learning method used when only a small fraction of labeled data is available, which implies solving a nonconvex optimization problem. Several approximation methods have been proposed to solve it, but they usually find suboptimal solutions. However, a global optimal solution may be obtained by using exact techniques, but at the cost of suffering an exponential time complexity with respect to the number of instances. In this article, an interpretation of TSVM in terms of violator space is given. A randomized method is presented that extends the use of exact methods, thus reducing the time complexity exponentially w.r.t. the number of support vectors of the optimal solution instead of exponentially w.r.t. the number of instances.