microsoft / microsoft/foldingdiff

Where is wrapped gaussian sampling done during noising?

Open
#25 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Jupyter Notebook
Stars
568
Forks
74
Avg merge
20h 2m
Merged PRs (30d)
1

Description

The only code where I see a loop over k is in ScoreMatchingNoisedAnglesDataset class.

I am not sure that I was able to find the use of the wrapped gaussian during generation of the noised samples. Can you point me to the relevant code where this is being done?

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by tracing the ScoreMatchingNoisedAnglesDataset class and its loop over k, then search the noising and generation entry points for wrapped Gaussian sampling. Done means identifying the relevant code path and documenting where the wrapped Gaussian is used.

Written by the indexing model from the issue text.

Assessment

Domain
machine-learning
Issue type
Documentation
Difficulty
1/5
Estimated time
Under an hour
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.