My starting point is http://edwardlib.org/tutorials/batch-training in which the tutorial makes a note of setting a scale factor of
Like the two related posts up the top i’m interested in running VI in a streaming context. Regarding the initialisation of ed.KLqp I have a few confusions
Is the scale parameter only relevant if one uses inference.run at first with N > M training data points.
Is n_samples only relevant if one uses an inference. run. call? I.e. if from the beginning if you have a large amount of data to train first on, and then the model is exposed to completely new data in a streaming situation. If not where does this fit in
In the case of having no data initially, and then acquiring data accumulating into buffers of size M, is it enough to simply have N=M giving a scale of 1 ?