FluxML / FluxML/Optimisers.jl

Grokfast exponential moving average Optimizer

Open
#176 0 comments 0 reactions 0 assignees View on GitHub
enhancement
Dominant language
Julia
Stars
96
Forks
30
PR merge metrics
No merged PRs in 30d

Description

### Motivation and description

Algorithm 2 in https://arxiv.org/pdf/2405.20233 should be a very easy implementation

### Possible Implementation

_No response_

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by reading Algorithm 2 in the linked paper and comparing its update rule with the existing optimizer entry points in Optimisers.jl. Confirm the implementation matches the paper and integrates with the repository's learning-loop usage; the issue does not name a file or test, so those locations must be identified first.

Written by the indexing model from the issue text.

Assessment

Tech stack
julia
Domain
machine-learning
Issue type
Feature
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.