jankrepl / jankrepl/deepdow

Clipping in gradient_wrt_input

Open
#32 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement
Dominant language
Python
Stars
1.2k
Forks
170
PR merge metrics
No merged PRs in 30d

Description

Currently, we implement one "Explainable" algorithm in `deepdow.explain.gradient_wrt_input`. The problem is that we do not restrict the values the input can have. One solution would be to implement some projection/clipping logic that takes place after each optimizer step and thus forces the values to be in a given range.

See https://arxiv.org/pdf/1702.04782.pdf

Contributor guide

No contributing guide indexed for this repository

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 deepdow.explain.gradient_wrt_input entry point and read the linked paper for the proposed projection or clipping approach. Determine how optimizer steps are performed and what input range should be enforced; done means the explainable algorithm keeps input values within that range after each step.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.