Convergence of Hyperbolic Neural Networks Under Riemannian Stochastic Gradient Descent
Convergence of Hyperbolic Neural Networks Under Riemannian Stochastic Gradient Descent
复制标题
黎曼随机梯度下降下双曲神经网络的收敛性
DOI:
10.1007/s42967-023-00302-9
复制
发表时间:
2023
影响因子:
1.6
通讯作者:
Xin, Jack
中科院分区:
文献类型:
--
作者:
Whiting, Wes;Wang, Bao;Xin, Jack
We prove, under mild conditions, the convergence of a Riemannian gradient descent method for a hyperbolic neural network regression model, both in batch gradient descent and stochastic gradient descent. We also discuss a Riemannian version of the Adam algorithm. We show numerical simulations of these algorithms on various benchmarks.