Cargando…
The Convex Information Bottleneck Lagrangian
The information bottleneck (IB) problem tackles the issue of obtaining relevant compressed representations T of some random variable X for the task of predicting Y. It is defined as a constrained optimization problem that maximizes the information the representation has about the task, [Formula: see...
Autores principales: | Rodríguez Gálvez, Borja, Thobaben, Ragnar, Skoglund, Mikael |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7516537/ https://www.ncbi.nlm.nih.gov/pubmed/33285873 http://dx.doi.org/10.3390/e22010098 |
Ejemplares similares
-
Lagrangian betweenness as a measure of bottlenecks in dynamical systems with oceanographic examples
por: Ser-Giacomi, Enrico, et al.
Publicado: (2021) -
Complex convexity and analytic functionals
por: Andersson, Mats, et al.
Publicado: (2004) -
Fast Augmented Lagrangian Method in the convex regime with convergence guarantees for the iterates
por: Boţ, Radu Ioan, et al.
Publicado: (2022) -
On the Difference between the Information Bottleneck and the Deep Information Bottleneck
por: Wieczorek, Aleksander, et al.
Publicado: (2020) -
Learnability for the Information Bottleneck
por: Wu, Tailin, et al.
Publicado: (2019)