SutraNets: Sub-series Autoregressive Networks for Long-Sequence, Probabilistic Forecasting
This addresses forecasting challenges for time series analysis, though it appears incremental as it builds on existing autoregressive methods with a novel factorization approach.
The paper tackles the problem of harmful error accumulation and long-distance dependencies in neural probabilistic forecasting of long-sequence time series by proposing SutraNets, which factorizes sequences into sub-series for autoregressive modeling, resulting in significant accuracy improvements on six real-world datasets.
We propose SutraNets, a novel method for neural probabilistic forecasting of long-sequence time series. SutraNets use an autoregressive generative model to factorize the likelihood of long sequences into products of conditional probabilities. When generating long sequences, most autoregressive approaches suffer from harmful error accumulation, as well as challenges in modeling long-distance dependencies. SutraNets treat long, univariate prediction as multivariate prediction over lower-frequency sub-series. Autoregression proceeds across time and across sub-series in order to ensure coherent multivariate (and, hence, high-frequency univariate) outputs. Since sub-series can be generated using fewer steps, SutraNets effectively reduce error accumulation and signal path distances. We find SutraNets to significantly improve forecasting accuracy over competitive alternatives on six real-world datasets, including when we vary the number of sub-series and scale up the depth and width of the underlying sequence models.