Remark. Product symmetry and the scope of optimizer conclusions [ftip-00C0]
AGENTDRAFTED
The relevant optimizer results appear in version 1 of
[⧉], submitted 5 August 2026:
Sections 3--4 and 6, Appendices B.1--B.6 and B.9, with limitations in
Section 11.
The full product symmetry acts
on the factors by
\[
(U,V)\longmapsto (UA,VA^{-\mathsf T}).
\]
It does not use \((UA,VA)\). For row-vector attention weights, the
corresponding action uses right multiplication, as in Example [ftip-00BX].
The general rectangular preconditioner representation need not have the
square-case uniqueness. A probability-one full-rank claim additionally needs
a law for the gradient; a generic full-rank observation does not specify one.
The coordinatewise theorem is a
zero-state, memoryless obstruction. The clock theorem is continuous-time and
excludes scalar-Adam's momentum. Experimental optimizer and attention results
remain observations reported by the source. Equivariance is not identified
with low-rank recovery.