pytorch / pytorch/benchmark

Add model with inner optimization loop to model repo

Open
#153 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
1k
Forks
346
PR merge metrics
No merged PRs in 30d

Description

An inner optimization loop is when the functional autograd API is used in the forward pass and then the user differentiates through it. Uses include MAML, Energy Based Models, and (shameless self plug) set generation.

Would be nice as it requires autograd in the forward pass, and requires higher order gradients in the backwards pass. Definitely more "researchy" code.

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

The issue does not name a file, test, or entry point. Start by reviewing the model repository's conventions and the linked MAML, energy-based model, and set-generation examples, then determine how an inner optimization loop should fit the benchmark collection. Done should mean a model using functional autograd in its forward pass and higher-order gradients in backward is added to the repository.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
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.