Timezone: »

End-to-End Learning of Coherent Probabilistic Forecasts for Hierarchical Time Series
Syama Sundar Yadav Rangapuram · Lucien Werner · Konstantinos Benidis · Pedro Mercado · Jan Gasthaus · Tim Januschowski

Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @

This paper presents a novel approach for hierarchical time series forecasting that produces coherent, probabilistic forecasts without requiring any explicit post-processing reconciliation. Unlike the state-of-the-art, the proposed method simultaneously learns from all time series in the hierarchy and incorporates the reconciliation step into a single trainable model. This is achieved by applying the reparameterization trick and casting reconciliation as an optimization problem with a closed-form solution. These model features make end-to-end learning of hierarchical forecasts possible, while accomplishing the challenging task of generating forecasts that are both probabilistic and coherent. Importantly, our approach also accommodates general aggregation constraints including grouped and temporal hierarchies. An extensive empirical evaluation on real-world hierarchical datasets demonstrates the advantages of the proposed approach over the state-of-the-art.

Author Information

Syama Sundar Yadav Rangapuram (Amazon)
Lucien Werner (California Institute of Technology)
Konstantinos Benidis (Amazon Research)
Pedro Mercado (Amazon Research)
Jan Gasthaus (AWS AI Labs)
Tim Januschowski (Amazon Research)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors