arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2005.08948cs.LGstat.ML
收藏

使用简单RNN实现LSTM的在线回归性能

Achieving Online Regression Performance of LSTMs with Simple RNNs

Bilkent University(比尔肯特大学);Turkcell Technology(Turkcell技术公司);DataBoss A.S.(DataBoss公司)

N. Mert Vural, Fatih Ilhan, Selim F. Yilmaz, Salih Ergüt, Suleyman S. Kozat

摘要:

递归神经网络(RNN)由于其泛化非线性时间依赖性的能力而被广泛用于在线回归。作为RNN模型,长短期记忆网络(LSTM)在实践中通常是首选的,因为这些网络能够学习长期依赖性,同时避免消失梯度问题。然而,由于它们的大量参数,与简单RNN(SRNN)相比,训练LSTM需要相当长的训练时间。在本文中,我们实现了在线回归性能的LSTM与SRNN有效。为此,我们引入了一个一阶训练算法的线性时间复杂度的参数的数量。我们表明,当用我们的算法训练SRNN时,它们在两到三倍的训练时间内提供了与LSTM非常相似的回归性能。我们提供强有力的理论分析,以支持我们的实验结果,我们的算法的收敛速度提供遗憾的界限。通过大量的实验,我们验证了我们的理论工作,并证明了我们的算法相对于LSTM和其他最先进的学习模型的显着性能改进。

英文摘要:

Recurrent Neural Networks (RNNs) are widely used for online regression due to their ability to generalize nonlinear temporal dependencies. As an RNN model, Long-Short-Term-Memory Networks (LSTMs) are commonly preferred in practice, as these networks are capable of learning long-term dependencies while avoiding the vanishing gradient problem. However, due to their large number of parameters, training LSTMs requires considerably longer training time compared to simple RNNs (SRNNs). In this paper, we achieve the online regression performance of LSTMs with SRNNs efficiently. To this end, we introduce a first-order training algorithm with a linear time complexity in the number of parameters. We show that when SRNNs are trained with our algorithm, they provide very similar regression performance with the LSTMs in two to three times shorter training time. We provide strong theoretical analysis to support our experimental results by providing regret bounds on the convergence rate of our algorithm. Through an extensive set of experiments, we verify our theoretical work and demonstrate significant performance improvements of our algorithm with respect to LSTMs and the other state-of-the-art learning models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑