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 1907.03329cs.LGstat.ML
收藏

快速ES-RNN:ES-RNN算法的GPU实现

Fast ES-RNN: A GPU Implementation of the ES-RNN Algorithm

Carnegie Mellon University(卡内基梅隆大学)

Andrew Redd, Kaung Khin, Aldo Marini

摘要:

由于其普遍性,时间序列预测在多个领域中至关重要。我们力求使国家的最先进的预测快速,可访问和推广。ES-RNN是经典状态空间预测模型和现代RNN的混合,在M4竞赛中实现了9.4%的sMAPE改进。至关重要的是,ES-RNN的实现需要每个时间序列的参数。通过对原始实现进行矢量化并将算法移植到GPU上,我们根据批量大小实现了高达322倍的训练加速,结果与原始提交中报告的结果相似。我们的代码可以在https://github.com/damitkwr/ESRNN-GPU上找到

英文摘要:

Due to their prevalence, time series forecasting is crucial in multiple domains. We seek to make state-of-the-art forecasting fast, accessible, and generalizable. ES-RNN is a hybrid between classical state space forecasting models and modern RNNs that achieved a 9.4% sMAPE improvement in the M4 competition. Crucially, ES-RNN implementation requires per-time series parameters. By vectorizing the original implementation and porting the algorithm to a GPU, we achieve up to 322x training speedup depending on batch size with similar results as those reported in the original submission. Our code can be found at: https://github.com/damitkwr/ESRNN-GPU

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。

↑