Methods › General › Generalization › Distributional Generalization
Distributional Generalization
Introduced by Preetum Nakkiran et al. in Distributional Generalization: A New Kind of Generalization
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Distributional Generalization is a type of generalization that roughly states that outputs of a classifier at train and test time are close as distributions, as opposed to close in just their average error. This behavior is not captured by classical generalization, which would only consider the average error and not the distribution of errors over the input domain.
Papers archive 2025-07-28
4 shown of 4, 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.
-
Learning Counterfactual Distributions via Kernel Nearest Neighbors 17 Oct 2024 · 1 repository · arXiv:2410.13381
-
What You See is What You Get: Principled Deep Learning via Distributional Generalization 7 Apr 2022 · 1 repository · arXiv:2204.03230Syntology ran 2 of 7 samples · 5 unverified
-
A Distributional Perspective on Actor-Critic Framework 1 Jan 2021 · 0 repositories
-
Distributional Generalization: A New Kind of Generalization 17 Sep 2020 · 1 repository · arXiv:2009.08092
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 |
|---|---|
| 2D Object Detection | 1 |
| Distributional Reinforcement Learning | 1 |
| Matrix Completion | 1 |
| counterfactual | 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