I have a model understanding question concerning the NHITS model. I am hoping to get some clarifications about the connection between two hyper-parameters:

n_freq_downsample

and

n_pool_kernel_size

. My question may also stem from how these parameters interact with one another. From my understanding, the higher the value in

n_freq_downsample

, the less datapoints we will have after downsampling. i.e. if we have daily data and we downsample with

n_freq_downsample = 7

, we will have 1/7 the amount of data.

n_pool_kernel_size

also has a "downsampling effect", if we have an input size of

N

and

n_pool_kernel_size = 2

, then we will now have

N / 2

datapoints. First of all, is this understanding correct? And if so, it seems like we would want these two hyperparameters be inversely proportional. I would not want to downsample by a large number and then apply large kernel size pooling layer. These would dramatically decrease the amount of information being fed into my model? The reason I am asking this question is because I was looking at the AutoNHITS parameter space

"n_pool_kernel_size": tune.choice(
            [[2, 2, 1], 3 * [1], 3 * [2], 3 * [4], [8, 4, 1], [16, 8, 1]]
        ),
        "n_freq_downsample": tune.choice(
            [
                [168, 24, 1],
                [24, 12, 1],
                [180, 60, 1],
                [60, 8, 1],
                [40, 20, 1],
                [1, 1, 1],
            ]
        ),

Intuitively, I would have assumed that the last two choices for

n_pool_kernel_size

would have been reversed. I.E.

[1, 4, 8], [1, 8, 16]

?

Hi @Phil! You understanding on both parameters is correct. Regarding the inverse, not necessarily. The

n_pool_kernel_size

downsamples only the inputs, and the

n_freq_downsample

only the output. Having both at the same time do not compound, because they affect different parts of the architecture. Here is the diagram of the paper, the kernel controls the Maxpool im the inputs of the MLP stack, and

n_freq_downsample

controls the output dimension of theta (points in the forecasting window)

I see that makes more sense! Thank you! Have you observed any effects of varying the number of blocks across frequencies. or keeping them constant is roughly equivalent in performance

We recommend increasing the blocks with larger datasets. For example, the NBEATS uses 30 blocks in total for each frequency of the M4 dataset, with around 30k series