AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Beyond Unit-Circle Eigenvalues: Invariant Bases for Stable State Space Dynamics

Jiaqian Zhu, Yang Zhang, Junhua Ding, Xiaowei Yu

NeurIPS 2026 · Probabilistic and scientific modeling › Dynamical systems · approach: State-space inference for stochastic systems · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes invariant-basis parameterizations for state space models to stabilize long-horizon dynamics beyond merely constraining eigenvalues to the unit circle.

Problem

Diagonal state space models become unstable over long horizons, where small spectral deviations compound into information decay or uncontrolled growth, especially for conservation-preserving or non-dissipative dynamics.

Approach

Argues that constraining eigenvalues to the unit circle is insufficient for long-horizon stability; proposes invariant bases beyond unit-circle eigenvalue constraints to stabilize state space dynamics.

Key results

Measured effects reported in the paper

What was changedWhereMeasuredEffect
constrain eigenvalues to unit modulus only (level B) instead of full Kronecker-Laplacian assembly (ablation)diagonal recurrence · Visual N-bodymomentum drift (%): 141 percent momentum drift with norm held at 4e-6Hurt
add Laplacian zero-row-sum condition (L1=0) on top of unit modulus (ablation)KC · Visual N-body perturbation testmomentum drift (%): 110 -> 3.5e-5Improved
Kronecker structure with Laplacian vs other norm-preserving operators (Haar, dense Cayley, diagonal unitary)operator level · 2000-step rolloutmomentum drift (%): 170.7 -> 4.0e-3Improved
tie decoder to the conserved quantity instead of an unconstrained decoder (ablation)KC · Dam-breakmass drift: 115 -> 8.3e-3Improved
assemble KC instead of any diagonal recurrencediagonal SSM · Allen-Cahnmass drift: 3.28 -> 2.0e-5Improved
apply output mass corrector (CPFNO) to neural operatorCPFNO · Dam-break, 100-step rolloutstability: four of five seeds diverge between steps 48 and 83Mixed
add fixed uniform mass corrector on FNOFNO · Dam-breakstability: diverges on every seed between steps 58 and 97Hurt
add momentum conservation penalty to a free orthogonal basis (ablation)free modal basis · Visual N-bodymomentum drift: drift 44 to 932 percent on 14 of 16 seedsHurt
increase training set size of a Hamiltonian network (ablation)Hamiltonian network · Visual N-bodymomentum drift (%): 16.9 -> 1.49Mixed
unitary KC step applied to dissipative dynamicsKC · Stiff reaction networkstate fit accuracyHurt
KC on N-body systems vs diagonal baselinesKC · N-body (charged, gravity, spring)linear momentum drift: 0.5 to 8 -> 2e-6Improved

Surprising findings

Limitations

Experimental setup

Metrics: dB gain at step 10

Baselines: unit-circle eigenvalue constraint

Builds on: diagonal state space models

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy