ant-research / ant-research/EasyTemporalPointProcess
[Question] NHP predicted rmse is instable on taxi data.
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 358
- Forks
- 51
- PR merge metrics
- No merged PRs in 30d
Description
When training the NHP model with the default taxi data and configuration, I observed that while log-likelihood improves over epochs, the time root-mean-square error (RMSE) does not converge, as shown in the figure below.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the NHP training run with the default taxi data and configuration, comparing RMSE and log-likelihood across epochs. Trace the NHP model and metric calculation used by that run; done means identifying whether the instability is expected or fixing it with evidence from a repeatable training result.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100