Fix Huber Loss gradient scaling - #420
Merged
Merged
Conversation
Contributor
There was a problem hiding this comment.
Pull request overview
Fixes the magnitude scaling bug in HuberLoss::differentiate() so the analytical gradient matches the implemented pseudo-Huber loss, and adds coverage to prevent regressions.
Changes:
- Correct gradient scaling in
HuberLoss::differentiate()by applying the missingalphafactor. - Add a numeric-gradient comparison test for
HuberLosswith a non-1.0 alpha. - Update the changelog with a new 2.5.3 entry (currently includes an unrelated item).
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
| src/NeuralNet/CostFunctions/HuberLoss.php | Applies the missing alpha factor so differentiate() matches the loss function’s true gradient magnitude. |
| tests/NeuralNet/CostFunctions/HuberLossTest.php | Adds a numeric-gradient regression test for differentiate() under alpha=0.5. |
| CHANGELOG.md | Adds a 2.5.3 entry, but currently lists an unrelated KNN fix not included in this PR. |
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
apphp
approved these changes
Aug 16, 2026
|
LGTM |
Member
Author
|
Should probably change the variable name of the local $alpha variable so it doesn't clash with the alpha hyper-parameter. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
src/NeuralNet/CostFunctions/HuberLoss.php:110 — differentiate returns e/√(e²+α²) while compute implements α²(√(1+(e/α)²)−1) whose true gradient is α·e/√(α²+e²) (missing factor α). Constant scale error; direction correct.