Evento
A Learning Algorithm with Compression-Based Regularization
Tipo del evento:
Conferencia
Nombre del evento:
International Conference on Acoustics, Speech and Signal Processing
Fecha del evento:
15/04/2018
Institución Organizadora:
Institute of Electrical and Electronics Engineers;
Título de la revista:
International Conference on Acoustics, Speech and Signal Processing
Editorial:
Institute of Electrical and Electronics Engineers
e-ISSN:
2379-190X
Idioma:
Inglés
Clasificación temática:
Resumen
This paper investigates, from information theoretic principles, a learning problem based on the principle that any regularity in a given dataset can be exploited to extract compact features from data, in order to build meaningful representations of a relevant content. We begin by introducing the fundamental tradeoff between the average risk and the model complexity. Interestingly, our formulation allows an information theoretic formulation of the multi-task learning (MTL) problem. Then, we present an iterative algorithm for computing the optimal tradeoffs. Remarkably, empirical results illustrate that there exists an optimal information rate minimizing the excess risk which depends on the nature and the amount of available training data. An application to hierarchical text categorization is also investigated, extending previous works.
Archivos asociados
Licencia
Identificadores
Colecciones
Eventos(CSC)
Eventos de CENTRO DE SIMULACION COMPUTACIONAL P/APLIC. TECNOLOGICAS
Eventos de CENTRO DE SIMULACION COMPUTACIONAL P/APLIC. TECNOLOGICAS
Citación
A Learning Algorithm with Compression-Based Regularization; International Conference on Acoustics, Speech and Signal Processing; Calgary; Canadá; 2018; 1-5
Compartir
Altmétricas