Hi everyone ! I was wondering if anyone knew of an open-source version of the CLOVER hierarchical TS model, it seems partially based on neuralforecast. In particular I'm trying to reproduce their specific version of the MQCNN but i'm not sure I understand how the MLP decoder is used ( it's different than the traditional MQCNN since this is a multivariate version but the paper isn't exactly explicit regarding how)

The closest we have currently in NF is HINT (paper) which was, very vaguely speaking, a previous version of CLOVER. Let's see if we get @Kin Gtz. Olivares to incorporate his new model into NF.

Hi, thank you for the reply ! I've also had some problems with using HINT in the past, do you know how it handles the reparametrization trick for making the mixture losses end-to-end ?

Hey @Owen Chaffard, it does not apply the reparameterization trick. It estimates the joint likelihood, instead of optimizing for the CRPS