Vidar

For VAR and VECM I would go for the **vars** package in R (https://cran.r-project.org/web/packages/vars/vignettes/vars.pdf). I've only used VAR/VECM to analyze impulse response functions. For forecasting I would always go for...

So I found a way for this to work. Not sure how it fit's into your package though. So after I create `lm_calib_mtbl` from above I run this code and...

Do you get the same results as I got?

There are severael questions on Matts slacks channel regarding this. I don't understand why exp() simply works now. So I tried to run my first example doing what you proposed,...

Hi @AlbertoAlmuinha, this is great news! I’ll run some test and let you know :)

I tried this using hist_exog_list: ``` nhits_config = { "max_steps": 100, # Number of SGD steps "input_size": 24, # Size of input window "learning_rate": tune.loguniform(1e-5, 1e-1), # Initial Learning rate...

I guess my question is how do I use known and static information when creating forecasts?

If I'm not mistaken, then `generics::forecast()` does not accept new_data while `predict()` does. The only thing that worked was to use `predict()` and then `bind_cols()` to get the id, Date,...

I've had this issue with DeepAR and then it was due to exploding gradients and I had to adjust the clip_gradient. I don't know the exact architecture of N-BEATS, but...

`torch::cuda_is_available()` is FALSE so I need to check on that. But I did not find anything in the code where I could set `device = "gpu"`.