标签:分布 decode models ssi ant lstm cas hit nbsp
2017 NIPS, time series workshop
traditional methods: ARIMA.
Seq2Seq
quantile forecast;
DeepAR, probabilistic forecasting with encoder-decoder models. A seq2seq architecture with an identical encoder and decoder.
为什么要用encoder-decoder 模型,是因为这个模型可以对分布进行拟合,是quantile regression model 的重要条件。
Loss: quantile loss
structure: encoder, lstm; decoder lstm.
PP: A multi-horizon quantile recurrent forecaster
标签:分布 decode models ssi ant lstm cas hit nbsp
原文地址:https://www.cnblogs.com/dulun/p/12256577.html