Joint Regularized Inverse (JRI) applies a capped inverse spectral map to the combined weight-bias momentum matrix and uses the transformed bias column as the physical bias update, yielding small consistent gains on BERT-mini/IMDb.
In: Interna- tional Conference on Learning Representations (2015) 17
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Joint Affine Spectral Shaping: Coupling Weight and Bias Updates Beyond Weight-Only Muon
Joint Regularized Inverse (JRI) applies a capped inverse spectral map to the combined weight-bias momentum matrix and uses the transformed bias column as the physical bias update, yielding small consistent gains on BERT-mini/IMDb.