Convergence of Hyperbolic Neural Networks Under Riemannian Stochastic Gradient Descent
COMMUNICATIONS ON APPLIED MATHEMATICS AND COMPUTATION(2023)
摘要
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.
更多查看译文
关键词
Hyperbolic neural network,Riemannian gradient descent,Riemannian Adam (RAdam),Training convergence
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要