Keywords: Sparse additive models, variable selection, Huber, non-stationary, robust forecasting
Abstract: Sparse additive models have shown promising ﬂexibility and interpretability in processing time series data. However, existing methods usually assume the time series data to be stationary and the innovation is sampled from a Gaussian distribution. Both assumptions are too stringent for heavy-tailed and non-stationary time series data that frequently arise in practice, such as ﬁnance and medical ﬁelds. To address these problems, we propose an adaptive sparse Huber additive model for robust forecasting in both non-Gaussian data and (non)stationary data. In theory, the generalization bounds of our estimator are established for both stationary and nonstationary time series data, which are independent of the widely used mixing conditions in learning theory of dependent observations. Moreover, the error bound for non-stationary time series contains a discrepancy measure for the shifts of the data distributions over time. Such a discrepancy measure can be estimated empirically and used as a penalty in our method. Experimental results on both synthetic and real-world benchmark datasets validate the effectiveness of the proposed method. The code is available at https://github.com/xianruizhong/SpHAM.
One-sentence Summary: An adaptive sparse Huber additive model for robust forecasting and variable selection in non-Gaussian and (non)stationary time series data