tensorflow / tensorflow/probability
Negative loss function in Autoregressive
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 4.4k
- Forks
- 1.1k
- PR merge metrics
- No merged PRs in 30d
Description
Hi
I'm using Autoregressive for density estimation, the same example that is written in this page:
However, when I increase the dimension (event_shape) of the data that I want to find its density, from two to four for example, I start getting negative loss function!
Can anyone help me with this issue.
Thanks
Contributor guide
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 with the TensorFlow Probability AutoregressiveNetwork example linked in the issue and reproduce it with event_shape two and four. Inspect how the density-estimation loss is computed and determine whether the reported negative value is reproducible; done means documenting the cause and a verified correction or explanation.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- tensorflow
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100