Methods › General › Robustness Methods › Fishr
Fishr
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Fishr is a learning scheme to enforce domain invariance in the space of the gradients of the loss function: specifically, it introduces a regularization term that matches the domain-level variances of gradients across training domains. Critically, the strategy exhibits close relations with the Fisher Information and the Hessian of the loss. Forcing domain-level gradient covariances to be similar during the learning procedure eventually aligns the domain-level loss landscapes locally around the final weights.
Papers archive 2025-07-28
2 shown of 2, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Understanding Hessian Alignment for Domain Generalization 22 Aug 2023 · 1 repository · arXiv:2308.11778Syntology ran 4 of 6 samples · 2 unverified · 6 pointer-only (licence)
-
Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization 7 Sep 2021 · 2 repositories · arXiv:2109.02934Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
Tasks archive 2025-07-28
4 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Domain Generalization | 2 |
| Autonomous Vehicles | 1 |
| Federated Learning | 1 |
| Out-of-Distribution Generalization | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections