z-logo
open-access-imgOpen Access
Beyond the Quadratic Approximation: The Multiscale Structure of Neural Network Loss Landscapes
Author(s) -
Chao Ma,
Daniel Kunin,
Lei Wu,
Lexing Ying
Publication year - 2022
Publication title -
journal of machine learning
Language(s) - English
Resource type - Journals
eISSN - 2790-2048
pISSN - 2790-203X
DOI - 10.4208/jml.220404
Subject(s) - maxima and minima , artificial neural network , quadratic equation , quadratic growth , gradient descent , convexity , quadratic function , computer science , stability (learning theory) , mathematics , mathematical optimization , statistical physics , algorithm , artificial intelligence , physics , mathematical analysis , machine learning , geometry , financial economics , economics

The content you want is available to Zendy users.

Already have an account? Click here to sign in.
Having issues? You can contact us here