arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.02438cs.LG
收藏

学习具有常数复杂度的 K-U-Net:在时间序列预测中的应用

Learning K-U-Net with constant complexity: An Application to time series forecasting

Université Paris-Est Créteil(巴黎东部克雷泰伊大学);ESIEE Paris(巴黎ESIEE高等电子与数字学院);HN-Services(HN服务公司)

Jiang You, Arben Cela, René Natowicz, Jacob Ouanounou, Patrick Siarry

AI总结:

针对时间序列预测中高层特征学习缓慢的问题,提出指数加权随机梯度下降算法,使 K-U-Net 训练达到常数时间复杂度,并在合成数据上同时提升测试精度。

摘要:

训练用于时间序列预测的深度模型是一项关键任务,其固有挑战在于时间复杂度。当前方法通常保证线性时间复杂度,但我们对时间冗余的观察表明,高层特征的学习速度比低层特征慢 98.44%。为解决这一问题,我们提出一种新的指数加权随机梯度下降算法,旨在深度学习模型中实现常数时间复杂度。我们证明了该学习方法的理论复杂度为常数。在合成数据集上对 Kernel U-Net(K-U-Net)进行该方法评估,结果显示复杂度显著降低,同时提高了测试集的准确性。

英文摘要:

Training deep models for time series forecasting is a critical task with an inherent challenge of time complexity. While current methods generally ensure linear time complexity, our observations on temporal redundancy show that high-level features are learned 98.44\% slower than low-level features. To address this issue, we introduce a new exponentially weighted stochastic gradient descent algorithm designed to achieve constant time complexity in deep learning models. We prove that the theoretical complexity of this learning method is constant. Evaluation of this method on Kernel U-Net (K-U-Net) on synthetic datasets shows a significant reduction in complexity while improving the accuracy of the test set.

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。

↑