# Low Dimensional Trajectory Hypothesis is True: DNNs can be Trained in Tiny Subspaces

> Research article (IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022) · cited 21× · AI/ML

**Wikidata**: [openalex:W4282939141](https://www.wikidata.org/wiki/openalex:W4282939141)  
**Source**: https://4ort.xyz/entity/low-dimensional-trajectory-hypothesis-is-true-dnns-can-be-trained-in-tiny-subspaces