On cheap entropy-sparsified regression learning

Regression learning is one of the long-standing problems in statistics, machine learning, and deep learning (DL). We show that writing this problem as a probabilistic expectation over (unknown) feature probabilities – thus increasing the number of unknown parameters and seemingly making the problem...

Descripción completa

Detalles Bibliográficos
Autores principales: Horenko, Illia, Vecchi, Edoardo, Kardoš, Juraj, Wächter, Andreas, Schenk, Olaf, O’Kane, Terence J., Gagliardini, Patrick, Gerber, Susanne
Formato: Online Artículo Texto
Lenguaje:English
Publicado: National Academy of Sciences 2022
Materias:
Physical Sciences
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9910478/
https://www.ncbi.nlm.nih.gov/pubmed/36580592
http://dx.doi.org/10.1073/pnas.2214972120

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9910478/
https://www.ncbi.nlm.nih.gov/pubmed/36580592
http://dx.doi.org/10.1073/pnas.2214972120

Ejemplares similares