On the Benefits of Invariance in Neural Networks.¶
Lyle, C., der Wilk, v., Kwiatkowska, Gal, & Bloem-Reddy, B. (2020). On the Benefits of Invariance in Neural Networks. arXiv preprint.
Cited by¶
1 citation across 1 artifact.
Each citation links to the sentence it supports in the citing article.
Primes¶
- Equivariance
- The prime names the relation; it does not adjudicate the modeling choice, a caution Lyle and colleagues (2020) raise when they show invariance and equivariance help only when the assumed symmetry genuinely holds in the data.
This sourceAnalyzes when building in invariance/equivariance helps (data augmentation and feature averaging), proving generalization benefits under the assumed invariant structure.
- The prime names the relation; it does not adjudicate the modeling choice, a caution Lyle and colleagues (2020) raise when they show invariance and equivariance help only when the assumed symmetry genuinely holds in the data.
Verification¶
Does it exist? Not checked yet. This entry carries no identifier to resolve. It was extracted from the citation as written in the article, normalized, and deduplicated against the rest of the registry.
Does it back the claim? Not recorded. The single citation of this work carries no recorded support check.
Was it audited? Yes. A second, independent pass read the citation against the article text and recorded a verdict.
Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.
See how references were verified.
Registry ID ref:d7684645b198 · see in the full table