Gated MLPs as Symmetry-Broken Rank-1 Bilinear Attention
Nathan Breslow
cs.LG cs.AI
Abstract
We show that the conventional gated MLP can be viewed as a rank-1 approximation to a bilinear attention mechanism with two distinct factors corresponding to the query and the key. We further show that moving the nonlinearity onto one factor breaks the exchange symmetry between the two factors and, for non-homogeneous activations, the inverse-scaling symmetry as well. This perspective may help explain why gated MLPs are effective in practice and inform the design of future architectures.
Topics
Classified with taxonomy v2 on Sat, 5 Sept 2026.