Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Nicholas Baskerville"'
Autor:
Nicholas Baskerville, Diego Granziol
Publikováno v:
Journal of Physics: Complexity. 3:024001
We conjecture that the inherent difference in generalisation between adaptive and non-adaptive gradient methods in deep learning stems from the increased estimation noise in the flattest directions of the true loss surface. We demonstrate that typica
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8d99c015fe52ac3547ac085f533acacb
https://doi.org/10.1088/2632-072x/ac730c
https://doi.org/10.1088/2632-072x/ac730c
