AI RESEARCH
L2RU: a Structured State Space Model with prescribed L2-bound
arXiv CS.LG
•
ArXi:2503.23818v3 Announce Type: replace-cross Structured state-space models (SSMs) have recently emerged as a powerful architecture at the intersection of machine learning and control, featuring layers composed of discrete-time linear time-invariant (LTI) systems followed by pointwise nonlinearities. These models combine the expressiveness of deep neural networks with the interpretability and inductive bias of dynamical systems, offering strong performance on long-sequence tasks with favorable computational complexity.