Publicación:
Efficient Projection onto the $\ell_{\infty,1}$ Mixed-Norm Ball Using a Newton Root Search Method
Efficient Projection onto the $\ell_{\infty,1}$ Mixed-Norm Ball Using a Newton Root Search Method
No hay miniatura disponible
Fecha
2019-01
Autores
Chau, Gustavo
Wohlberg, Brendt
Rodriguez, Paul
Título de la revista
Revista ISSN
Título del volumen
Editor
Society for Industrial & Applied Mathematics (SIAM)
Proyectos de investigación
Unidades organizativas
Número de la revista
Abstracto
Mixed norms that promote structured sparsity have numerous applications in signal processing and machine learning problems. In this work, we present a new algorithm, based on a Newton root search technique, for computing the projection onto the ℓ∞,1 ball, which has found application in cognitive neuroscience and classification tasks. Numerical simulations show that our proposed method is between 8 and 10 times faster on average, and up to 20 times faster for very sparse solutions, than the previous state of the art. Tests on real functional magnetic resonance image data show that, for some data distributions, our algorithm can obtain speed improvements by a factor of between 10 and 100, depending on the implementation
Descripción
Palabras clave
regularización de la proyección,
Normas mixtas,
espaciosidad estructurada,
encontrar la raíz