Reproducing the results in "Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flows" in need of Parameters

zalandoresearch / pytorch-ts

PyTorch based Probabilistic Time Series forecasting framework based on GluonTS backend

MIT License

1.21k stars 191 forks source link

Reproducing the results in "Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flows" in need of Parameters #165

Open Usama-Samad opened 3 months ago

Usama-Samad commented 3 months ago

Hello,

Im trying to reproduce the results for all the datasets mentioned in the paper, but in examples of pytorch-ts there are only two examples with solar and traffic dataset

I’d really appreciate it if you could provide your hyperparamer settings for all the remaining datasets: Exchange, Electricity, Taxi, Wikipedia Respectively for all the models GRU-Real NVP, GRU-MAF and Transformer-MAF

Would really appreciate your help.