unit8co/darts
Voir sur GitHubImprove numerical stability of the NLL computation for some distributions
Open
#621 ouverte le 1 déc. 2021
good first issueimprovement
Métriques du dépôt
- Stars
- (6 832 stars)
- Métriques de merge PR
- (Merge moyen 143j 16h) (16 PRs mergées en 30 j)
Description
Not all Likelihoods have numerically-stable computaiton of the NLL. By default, we rely on the log_prob() function of the PyTorch Distribution objects, but it might not be the best way to get numerically stable gradients. I think it’s fairly easy to build cases where Negative Binomial fails for instance.
See: #663
Also for the Weibull distribution, the outputs changed when we changed the shape of the network outputs, which is weird and ideally should be investigated. Not clear if that’s due to numerical instability…