Deep Frank-Wolfe for neural network optimization
Learning a deep neural network requires solving a challenging optimization problem: it is a high-dimensional, non-convex and non-smooth minimization problem with a large number of terms. The current practice in neural network optimization is to rely on the stochastic gradient descent (SGD) algorithm...
Autori principali: | Berrada, L, Zisserman, A, Kumar, MP |
---|---|
Natura: | Internet publication |
Lingua: | English |
Pubblicazione: |
arXiv
2018
|
Documenti analoghi
Documenti analoghi
-
Deep Frank-Wolfe for neural network optimization
di: Berrada, L, et al.
Pubblicazione: (2019) -
Training neural networks for and by interpolation
di: Berrada, L, et al.
Pubblicazione: (2020) -
Riemannian Optimization via Frank-Wolfe Methods
di: Weber, Melanie, et al.
Pubblicazione: (2022) -
Riemannian optimization via Frank-Wolfe methods
di: Weber, M, et al.
Pubblicazione: (2022) -
New analysis and results for the Frank–Wolfe method
di: Freund, Robert Michael, et al.
Pubblicazione: (2016)