AI RESEARCH

DAGGER: Gradient-Free Construction of Transiently Amplifying Networks under Hard Connectivity Constraints

arXiv CS.LG

ArXi:2606.01227v1 Announce Type: new Many networks not only but also rely on transient non-normal amplification, an orders-of-magnitude increase in the activity of an otherwise stable system. Constructing such networks under hard sign/sparsity/diagonal constraints -- the regime relevant for biological connectomes and structured RNN initializations -- has so far required either gradient-based local search with thousands of inner-loop eigendecompositions or Schur-form direct construction in an abstract basis that breaks the constraints under projection.