AI RESEARCH
Universality of first-order methods on random and deterministic matrices
arXiv CS.LG
•
ArXi:2604.11729v1 Announce Type: cross General first-order methods (GFOM) are a flexible class of iterative algorithms which update a state vector by matrix-vector multiplications and entrywise nonlinearities. A long line of work has sought to understand the large-n dynamics of GFOM, mostly focusing on "very random" input matrices and the approximate message passing (AMP) special case of GFOM whose state is asymptotically Gaussian.