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...
主要な著者: | Berrada, L, Zisserman, A, Kumar, MP |
---|---|
フォーマット: | Internet publication |
言語: | English |
出版事項: |
arXiv
2018
|
類似資料
-
Deep Frank-Wolfe for neural network optimization
著者:: Berrada, L, 等
出版事項: (2019) -
Training neural networks for and by interpolation
著者:: Berrada, L, 等
出版事項: (2020) -
Riemannian Optimization via Frank-Wolfe Methods
著者:: Weber, Melanie, 等
出版事項: (2022) -
Riemannian optimization via Frank-Wolfe methods
著者:: Weber, M, 等
出版事項: (2022) -
New analysis and results for the Frank–Wolfe method
著者:: Freund, Robert Michael, 等
出版事項: (2016)