论文标题
训练时间序列域的强大深层模型：新型算法和理论分析
Training Robust Deep Models for Time-Series Domain: Novel Algorithms and Theoretical Analysis
论文作者
论文摘要
尽管深度神经网络（DNNS）成功地超过了时间序列数据（例如移动健康），但由于与图像和文本数据相比，由于其独特的特征，如何培训强大的DNN为时间序列域而闻名。在本文中，我们提出了一种新颖的算法框架，称为时间序列（RO-TS）的强大培训，以创建适合时间序列分类任务的强大DNN。具体而言，我们通过根据基于全局对齐内核（GAK）距离测量的时间序列输入来明确推理稳健性标准，从而在模型参数上提出了最小的最大优化问题。我们还使用gak和动态时间扭曲（DTW）来表明使用求和结构与时间序列对齐的求和结构的普遍性和优势。这个问题是一个组成的最低 - 最大优化问题家族的一个实例，这是具有挑战性的，并且没有明确的理论保证。我们为这个优化问题家族提出了一种原则上的随机组成交流梯度下降（SCAGDA）算法。与需要近似距离度量计算的时间序列的传统方法不同，SCAGDA使用移动平均值接近基于GAK的距离。我们理论上分析了SCAGDA的收敛速率，并为基于GAK的距离的估计提供了强大的理论支持。我们对现实世界基准测试的实验表明，与对抗性训练相比，使用依赖数据增强或损失函数的新定义的对抗训练相比，RO-TS会创建更强大的DNN。我们还证明了GAK在欧几里得距离上的时间序列数据的重要性。 RO-TS算法的源代码可在https://github.com/tahabelkhouja/robust-training-for-time-series上获得
Despite the success of deep neural networks (DNNs) for real-world applications over time-series data such as mobile health, little is known about how to train robust DNNs for time-series domain due to its unique characteristics compared to images and text data. In this paper, we propose a novel algorithmic framework referred as RObust Training for Time-Series (RO-TS) to create robust DNNs for time-series classification tasks. Specifically, we formulate a min-max optimization problem over the model parameters by explicitly reasoning about the robustness criteria in terms of additive perturbations to time-series inputs measured by the global alignment kernel (GAK) based distance. We also show the generality and advantages of our formulation using the summation structure over time-series alignments by relating both GAK and dynamic time warping (DTW). This problem is an instance of a family of compositional min-max optimization problems, which are challenging and open with unclear theoretical guarantee. We propose a principled stochastic compositional alternating gradient descent ascent (SCAGDA) algorithm for this family of optimization problems. Unlike traditional methods for time-series that require approximate computation of distance measures, SCAGDA approximates the GAK based distance on-the-fly using a moving average approach. We theoretically analyze the convergence rate of SCAGDA and provide strong theoretical support for the estimation of GAK based distance. Our experiments on real-world benchmarks demonstrate that RO-TS creates more robust DNNs when compared to adversarial training using prior methods that rely on data augmentation or new definitions of loss functions. We also demonstrate the importance of GAK for time-series data over the Euclidean distance. The source code of RO-TS algorithms is available at https://github.com/tahabelkhouja/Robust-Training-for-Time-Series
