Soft-DTW:时间序列的可微损失函数
Soft-DTW: a Differentiable Loss Function for Time-Series
摘要:
在本文中,我们提出了一个可区分的学习损失之间的时间序列,建立在著名的动态时间规整(DTW)的差异。与欧几里德距离不同,DTW可以比较可变大小的时间序列,并且对时间维度上的移位或移位具有鲁棒性。为了计算DTW,通常使用动态规划来解决两个时间序列之间的最小成本对齐问题。我们的工作利用了DTW的平滑公式,称为软DTW,计算所有对齐成本的软最小值。本文证明了软DTW是一个可微损失函数,其值和梯度都可以用二次时间/空间复杂度计算(DTW具有二次时间但线性空间复杂度)。我们表明,这种正则化是特别适合平均和集群的DTW几何下的时间序列,我们的建议显着优于现有的基线的任务。接下来,我们建议调整机器的参数,输出时间序列,最大限度地减少其与地面实况标签在软DTW意义上。
英文摘要:
We propose in this paper a differentiable learning loss between time series, building upon the celebrated dynamic time warping (DTW) discrepancy. Unlike the Euclidean distance, DTW can compare time series of variable size and is robust to shifts or dilatations across the time dimension. To compute DTW, one typically solves a minimal-cost alignment problem between two time series using dynamic programming. Our work takes advantage of a smoothed formulation of DTW, called soft-DTW, that computes the soft-minimum of all alignment costs. We show in this paper that soft-DTW is a differentiable loss function, and that both its value and gradient can be computed with quadratic time/space complexity (DTW has quadratic time but linear space complexity). We show that this regularization is particularly well suited to average and cluster time series under the DTW geometry, a task for which our proposal significantly outperforms existing baselines. Next, we propose to tune the parameters of a machine that outputs time series by minimizing its fit with ground-truth labels in a soft-DTW sense.
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。