trends.barnas.net

phenomenon · first seen 26 Oct 2026

effective rank compression of weight matrices

Also: rank compression

The decrease in effective rank of neural network weight matrices during training, linked to phase transitions in learning.

Mentions per week

0119 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

grokkingmodular arithmetic task for transformers