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.

翻译：本文提出SutraNets，一种用于长序列时间序列神经概率预测的新方法。SutraNets采用自回归生成模型，将长序列的似然函数分解为条件概率的乘积。在生成长序列时，大多数自回归方法存在有害的误差累积问题，同时难以对长距离依赖关系进行建模。SutraNets将单变量长序列预测转化为低频子序列上的多变量预测，通过跨时间步与跨子序列的自回归过程，确保产生连贯的多变量（即高频单变量）输出。由于子序列生成所需步数更少，SutraNets有效减少了误差累积并缩短了信号路径距离。实验表明，在六个真实数据集上，SutraNets的预测精度显著优于竞争性替代方案，且该优势在改变子序列数量、扩大底层序列模型深度与宽度时依然成立。