Temporal covariate shift
10 Aug 2021 Yuntao Du, et al.AdaRNN: Adaptive Learning and Forecasting of Time Series
the statistical properties of a time series can vary with time, causing the distribution to change temporally, which is known as the distribution shift problem. … Adaptive RNNs (AdaRNN) to tackle the Temporal Covariate Shift (TCS) problem. AdaRNN is sequentially composed of two modules.
- The first module is referred to as Temporal Distribution Characterization, which aims to better characterize the distribution information in a time series.
- The second module is termed as Temporal Distribution Matching, which aims to reduce the distribution mismatch in the time series to learnan RNN-based adaptive time series prediction model.
