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...
Główni autorzy: | Berrada, L, Zisserman, A, Kumar, MP |
---|---|
Format: | Internet publication |
Język: | English |
Wydane: |
arXiv
2018
|
Podobne zapisy
-
Deep Frank-Wolfe for neural network optimization
od: Berrada, L, i wsp.
Wydane: (2019) -
Training neural networks for and by interpolation
od: Berrada, L, i wsp.
Wydane: (2020) -
Riemannian Optimization via Frank-Wolfe Methods
od: Weber, Melanie, i wsp.
Wydane: (2022) -
Riemannian optimization via Frank-Wolfe methods
od: Weber, M, i wsp.
Wydane: (2022) -
New analysis and results for the Frank–Wolfe method
od: Freund, Robert Michael, i wsp.
Wydane: (2016)