arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1903.05071cs.NEcs.LGstat.ML
收藏

时间序列数据集回声状态网络的有效优化

Efficient Optimization of Echo State Networks for Time Series Datasets

Harvard University(哈佛大学);Heidelberg Institute for Theoretical Studies(海德堡理论研究所)

Jacob Reinier Maat, Nikos Gianniotis, Pavlos Protopapas

摘要:

回声状态网络(ESN)是递归神经网络,它只训练它们的输出层,从而排除了通过时间反向传播梯度的需要,这导致了显著的计算增益。然而,ESN中的一个常见问题是确定其超参数,这些超参数在实例化表现良好的储层中至关重要,但通常手动设置或使用解析法设置。在这项工作中,我们优化ESN超参数使用贝叶斯优化,给出了有限的预算的功能评估,优于网格搜索策略。在大量时间序列数据的背景下,例如天文学领域的光变曲线,我们可以进一步降低ESN的优化成本。特别是,我们希望避免调整每个时间序列的超参数,因为这是昂贵的;相反,我们希望找到具有超参数的ESN,这些超参数不仅在单个时间序列上表现良好,而且在类似时间序列的组上表现良好,而不会显着牺牲预测性能。这自然导致了集群的概念,其中每个集群由一个ESN表示,该ESN被调整为对一组具有相似时间行为的时间序列进行建模。我们证明了这种方法的合成数据集和现实世界的光变曲线从CITRO调查。我们表明,我们的方法可以显著减少对整个数据集进行建模所需的ESN模型的数量,同时保留每个集群中系列的预测性能。

英文摘要:

Echo State Networks (ESNs) are recurrent neural networks that only train their output layer, thereby precluding the need to backpropagate gradients through time, which leads to significant computational gains. Nevertheless, a common issue in ESNs is determining its hyperparameters, which are crucial in instantiating a well performing reservoir, but are often set manually or using heuristics. In this work we optimize the ESN hyperparameters using Bayesian optimization which, given a limited budget of function evaluations, outperforms a grid search strategy. In the context of large volumes of time series data, such as light curves in the field of astronomy, we can further reduce the optimization cost of ESNs. In particular, we wish to avoid tuning hyperparameters per individual time series as this is costly; instead, we want to find ESNs with hyperparameters that perform well not just on individual time series but rather on groups of similar time series without sacrificing predictive performance significantly. This naturally leads to a notion of clusters, where each cluster is represented by an ESN tuned to model a group of time series of similar temporal behavior. We demonstrate this approach both on synthetic datasets and real world light curves from the MACHO survey. We show that our approach results in a significant reduction in the number of ESN models required to model a whole dataset, while retaining predictive performance for the series in each cluster.

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。

↑