Hello.
I read "ScoreGrad: Multivariate Probabilistic Time Series Forecasting with Continuous Energy-based Generative Models".
How did you decide epochs?
I would appreciate your cooperation.
We use grid-search method for hyper-parameter settings.
It's a good question, as we noted in the paper and appendix, the value of the train loss is not directly correlated with the performance.
Hello.
I read "ScoreGrad: Multivariate Probabilistic Time Series Forecasting with Continuous Energy-based Generative Models".
How did you decide epochs? I would appreciate your cooperation.