S-Crescendo: A Nested Transformer Weaving Framework for Scalable Nonlinear System in S-Domain Representation

Junlang Huang, Chen Hao, Li Luo, Yong Cai, Lexin Zhang, Tianhao Ma, Yitian Zhang, Zhong Guan

Keywords: nonlinear systems, VLSI backend design, transformer, transfer function

TL;DR: Our method decomposes n-th order transfer functions into first-order modal terms, bypasses conventional matrix-based iterations and efficiently reduces computational complexity from O(n^3) to linear O(n).

Abstract: Simulation of high-order nonlinear system requires extensive computational resources, especially in modern VLSI backend design where bifurcation-induced instability and chaos-like transient behaviors pose challenges. We present S-Crescendo - a nested transformer weaving framework that synergizes S-domain with neural operators for scalable time-domain prediction in high-order nonlinear networks, alleviating the computational bottlenecks of conventional solvers via Newton-Raphson method. By leveraging the partial-fraction decomposition of an n-th order transfer function into first-order modal terms with repeated poles and residues, our method bypasses the conventional Jacobian matrix-based iterations and efficiently reduces computational complexity from cubic $O(n^3)$ to linear $O(n)$.The proposed architecture seamlessly integrates an S-domain encoder with an attention-based correction operator to simultaneously isolate dominant response and adaptively capture higher-order non-linearities. Validated on order-1 to order-10 networks, our method achieves up to 0.99 test-set \(R^2\) accuracy against HSPICE golden waveforms and accelerates simulation by up to 18\(\times\), providing a scalable, physics-aware framework for high-dimensional nonlinear modeling.

Primary Area: Machine learning for sciences (e.g. climate, health, life sciences, physics, social sciences)

Submission Number: 27836