This message was deleted.

Hi @J.! Yes, you need to specify the list of variables in the config dictionary as with all other hyperparameters. For example:

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
       "n_pool_kernel_size": tune.choice([[2, 2, 2], [16, 8, 1]]),               # MaxPool's Kernelsize
       "n_freq_downsample": tune.choice([[168, 24, 1], [24, 12, 1], [1, 1, 1]]), # Interpolation expressivity ratios
       "val_check_steps": 50,                                                    # Compute validation every 50 steps
       "random_seed": tune.randint(1, 10),                                       # Random seed
       "futr_exog_list": [YOUR_LIST] # <-------------
    }

Thanks! I'll give that a try.

@J. by listing the future exo covariates, how does nhits_config sample this space? For example, if there are 10 covariates being listed, will the hyperparameter try different combinations of the 10 covariates for the optimal parameters?