NAMSG: An Efficient Method For Training Neural Networks.
Year: 2019
Type: preprint
Abstract: We introduce NAMSG, an adaptive first-order algorithm for training neuralnetworks. The method is efficient in computation and memory, and is
straightforward to implement. It computes the gradients at configurable remote
observation points, in order to expedite the convergence by adjusting the step
size for directions with different curvatures in the stochastic setting. It
also scales the updating vector elementwise by a nonincreasing preconditioner
to take the advantages of AMSGRAD. We analyze the convergence properties for
both convex and nonconvex problems by modeling the training process as a
dynamic system, and provide a strategy to select the observation factor without
grid search. A data-dependent regret bound is proposed to guarantee the
convergence in the convex setting. The method can further achieve a $O(log(T))$
regret bound for strongly convex functions. Experiments demonstrate that NAMSG
works well in practical problems and compares favorably to popular adaptive
methods, such as ADAM, NADAM, and AMSGRAD.
Source: arXiv (Cornell University)
Authors: Yushu Chen, Hao Jing, Wenlai Zhao, Zhiqiang Liu, Ouyi Li, Liang Qiao, Haohuan Fu, Wei Xue, Guangwen Yang
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2943296448