Streaming Adaptation of Deep Forecasting Models using Adaptive Recurrent Units
This addresses the need for memory-efficient and responsive adaptation in streaming time-series forecasting, though it is incremental as it builds on existing global and local modeling approaches.
The paper tackles the problem of adapting deep time-series forecasting models to streaming data by introducing ARU, an Adaptive Recurrent Unit that combines global deep learning with local linear models, requiring only fixed-sized state and enabling efficient updates. Results show ARU is more effective than recent local adaptation methods across several datasets.
We present ARU, an Adaptive Recurrent Unit for streaming adaptation of deep globally trained time-series forecasting models. The ARU combines the advantages of learning complex data transformations across multiple time series from deep global models, with per-series localization offered by closed-form linear models. Unlike existing methods of adaptation that are either memory-intensive or non-responsive after training, ARUs require only fixed sized state and adapt to streaming data via an easy RNN-like update operation. The core principle driving ARU is simple --- maintain sufficient statistics of conditional Gaussian distributions and use them to compute local parameters in closed form. Our contribution is in embedding such local linear models in globally trained deep models while allowing end-to-end training on the one hand, and easy RNN-like updates on the other. Across several datasets we show that ARU is more effective than recently proposed local adaptation methods that tax the global network to compute local parameters.