tensorflow / tensorflow/probability
Max_iterations parameter, L-BFGS
Open
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 4.4k
- Forks
- 1.1k
- PR merge metrics
- No merged PRs in 30d
Description
Is there a way to set a fixed number of iterations done by L-BFGS? The max_iterations parameter does not seem to work as it most of the time iterates a lot more. I would need it to perform exactly one iteration, but when setting the max_iterations to 1 it performs on average 4.
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
Reproduce the L-BFGS behavior with max_iterations set to 1 and measure how many iterations are actually performed. Trace the L-BFGS entry point and its iteration or stopping logic; done means the parameter reliably produces exactly one iteration, with a regression test covering this case.
Written by the indexing model from the issue text.
Assessment
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 30/100