Every Local Minimum Value Is the Global Minimum Value of Induced Model in Nonconvex Machine Learning

Every Local Minimum Value Is the Global Minimum Value of Induced Model in Nonconvex Machine Learning

For nonconvex optimization in machine learning, this article proves that every local minimum achieves the globally optimal value of the perturbable gradient basis model at any differentiable point. As a result, nonconvex machine learning is theoretically as supported as convex machine learning with...

Descrizione completa

Dettagli Bibliografici
Autori principali: Kawaguchi, Kenji, Huang, Jiaoyang, Kaelbling, Leslie P
Altri autori: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Natura: Articolo
Lingua:English
Pubblicazione: MIT Press - Journals 2021
Accesso online:https://hdl.handle.net/1721.1/129666

Accesso online

https://hdl.handle.net/1721.1/129666

Documenti analoghi