ML4GW / ML4GW/DeepClean

Hyperparameter search

Open
#7 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

hyperparameters research topic
Dominant language
Python
Stars
10
Forks
6
PR merge metrics
No merged PRs in 30d

Description

Include hyperparameter search as part of the "training" portion of all projects to ensure that hypotheses are validated or rejected with confidence.

I have been working on a distributed HP search library called nonvex which uses canned HP optimizers from Keras Tuner without introducing extra dependencies or code overhead to your existing training functions. I almost have this implemented in the context of projects/training to demonstrate how it works, and will update this issue with instructions/explanation when I do.

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 in projects/training and review the existing work described in the issue, along with the nonvex library and its Keras Tuner optimizers. Determine how hyperparameter search should be included across all projects' training portions. Done means training supports the search and the issue's promised instructions and explanation are available.

Written by the indexing model from the issue text.

Assessment

Tech stack
keras, machine-learning, python
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.