Symmetry-Protected Lyapunov Neutral Modes in Equivariant Recurrent Networks
Fuente:
arXiv
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913089161527296 |
|---|---|
| author | Mo, Hanson Hanxuan |
| author_facet | Mo, Hanson Hanxuan |
| contents | Recurrent networks that store position, phase, or other continuous variables need state-space directions that remain neutral over long horizons. We give a symmetry-based account of when such neutral directions are guaranteed rather than merely tuned. For a finite-dimensional autonomous \(C^1\) vector field equivariant under a Lie group \(G\), we prove that any compact invariant set carrying a uniformly nondegenerate group-orbit bundle with stabilizer type \(H\) has, at points where the Lyapunov spectrum is defined, at least \(\dim(G/H)\) zero Lyapunov exponents tangent to the group orbit. These symmetry-protected modes have zero group-tangent growth because of exact equivariance and orbit geometry. When this protection is explicitly broken, the formerly protected direction can acquire a pseudo-gap; in our controlled breaking experiments this pseudo-gap predicts finite memory lifetime. We verify the finite-dimensional consequences with normalized equivariance error, direct group-tangent exponents, principal-angle alignment, autonomous-flow-zero controls, and orbit-dimension scaling across \(S^1\), \(T^q\), \(SO(n)\), \(U(m)\), product-group, and coupled equivariant RNN-style systems. We also train an exactly equivariant recurrent cell on velocity-input \(S^1\) path integration across six seeds and compare it with matched GRU, LSTM, and orthogonal-RNN baselines. The learned equivariant cell preserves step equivariance to \(3.2\times10^{-8}\), has a near-zero group-tangent exponent under the zero-input autonomous restriction, and improves horizon, speed, and restricted-phase generalization in this matched protocol. The learned task results are consequence evidence; the theorem-level evidence remains exact equivariance, group-tangent exponents, orbit-dimension scaling, and tangent-subspace alignment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_03338 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Symmetry-Protected Lyapunov Neutral Modes in Equivariant Recurrent Networks Mo, Hanson Hanxuan Neural and Evolutionary Computing Dynamical Systems Recurrent networks that store position, phase, or other continuous variables need state-space directions that remain neutral over long horizons. We give a symmetry-based account of when such neutral directions are guaranteed rather than merely tuned. For a finite-dimensional autonomous \(C^1\) vector field equivariant under a Lie group \(G\), we prove that any compact invariant set carrying a uniformly nondegenerate group-orbit bundle with stabilizer type \(H\) has, at points where the Lyapunov spectrum is defined, at least \(\dim(G/H)\) zero Lyapunov exponents tangent to the group orbit. These symmetry-protected modes have zero group-tangent growth because of exact equivariance and orbit geometry. When this protection is explicitly broken, the formerly protected direction can acquire a pseudo-gap; in our controlled breaking experiments this pseudo-gap predicts finite memory lifetime. We verify the finite-dimensional consequences with normalized equivariance error, direct group-tangent exponents, principal-angle alignment, autonomous-flow-zero controls, and orbit-dimension scaling across \(S^1\), \(T^q\), \(SO(n)\), \(U(m)\), product-group, and coupled equivariant RNN-style systems. We also train an exactly equivariant recurrent cell on velocity-input \(S^1\) path integration across six seeds and compare it with matched GRU, LSTM, and orthogonal-RNN baselines. The learned equivariant cell preserves step equivariance to \(3.2\times10^{-8}\), has a near-zero group-tangent exponent under the zero-input autonomous restriction, and improves horizon, speed, and restricted-phase generalization in this matched protocol. The learned task results are consequence evidence; the theorem-level evidence remains exact equivariance, group-tangent exponents, orbit-dimension scaling, and tangent-subspace alignment. |
| title | Symmetry-Protected Lyapunov Neutral Modes in Equivariant Recurrent Networks |
| topic | Neural and Evolutionary Computing Dynamical Systems |
| url | https://arxiv.org/abs/2605.03338 |