SciML / SciML/EasyModelAnalysis.jl

Stopping criteria in the callback

Open
#159 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Julia
Stars
87
Forks
14
Avg merge
21h 12m
Merged PRs (30d)
19

Description

  • Absolute tolerance to stop at for the gradient
  • If we have validation data, then stop of "validation starts to go up"
    • Come up with a good heuristic
    • Don't need to store previous data
  • Support a stop button via a global boolean for exiting

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 with the callback implementation and trace how gradient and validation data are currently exposed. Determine how the requested absolute tolerance, validation increase heuristic, and global-boolean stop button should be observed. Done means the callback supports all three stopping conditions and exits when any requested condition is met.

Written by the indexing model from the issue text.

Assessment

Tech stack
julia
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.