Encoding Temporal Statistical-space Priors via Augmented Representation
This work addresses pervasive issues in time series modeling for practitioners, though it appears incremental as it builds on existing representation techniques.
The paper tackles challenges in time series forecasting such as high noise-to-signal ratio and non-stationarity by introducing a representation augmentation technique called Statistical-space Augmented Representation (SSAR), which significantly outperforms five up-to-date baselines on two datasets.
Modeling time series data remains a pervasive issue as the temporal dimension is inherent to numerous domains. Despite significant strides in time series forecasting, high noise-to-signal ratio, non-normality, non-stationarity, and lack of data continue challenging practitioners. In response, we leverage a simple representation augmentation technique to overcome these challenges. Our augmented representation acts as a statistical-space prior encoded at each time step. In response, we name our method Statistical-space Augmented Representation (SSAR). The underlying high-dimensional data-generating process inspires our representation augmentation. We rigorously examine the empirical generalization performance on two data sets with two downstream temporal learning algorithms. Our approach significantly beats all five up-to-date baselines. Moreover, the highly modular nature of our approach can easily be applied to various settings. Lastly, fully-fledged theoretical perspectives are available throughout the writing for a clear and rigorous understanding.