finding
active
finding:wide-toy-models-show-lower-gradient-cosine-similarity-between-frequent-and-rare-gradients-so-frequent-updates-do-not-overwrite-rare-features

Wide toy models show lower gradient cosine similarity between frequent and rare gradients, so frequent updates do not overwrite rare features

Fig. 4 caption.

Source paper

extracted_from
Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention
(2026) · Jing Huang · Daniel Wurgaft · Rachit Bansal · Laura Ruis +5

Neighborhood — ranked by edge-count

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.