Symmetry-Protected Lyapunov Neutral Modes in Equivariant Recurrent Networks

• URL: http://arxiv.org/abs/2605.03338v1
• Date: Tue, 05 May 2026 03:59:56 GMT
• Title: Symmetry-Protected Lyapunov Neutral Modes in Equivariant Recurrent Networks
• Abstract summary: Recurrent networks that store position, phase, or other continuous variables need state-space directions that remain neutral over long horizons.<n>We prove that any compact invariant set carrying a uniformly nondegenerate group-orbit bundle with stabilizer type (H) has, at least (dim(G/H)) zero Lyapunov exponents tangent to the group orbit.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Interior skin focusing and directional mirror transfer in a graded non-Hermitian Krawtchouk network [0.0]
  We study a finite open Krawtchouk network with oppositely graded directed hoppings.<n>For a broad intermediate range of asymmetries, their local imaginary gauge field changes sign in the bulk.
  arXiv  Detail & Related papers  (2026-08-19T10:56:53Z)
• Quotient Dynamics, Effective Curvature, and Implicit Bias in Positive Quadratic Networks [0.0]
  Positive quadratic networks admit the lowrank representation f_U(x)=xtop UUtop x, where UinmathbbRdtimes r is identifiable only up to right multiplication.<n>We study how this quotient structure governs training dynamics, curvature, recovery, and bias.
  arXiv  Detail & Related papers  (2026-07-28T12:04:46Z)
• Is Spurious Correlation Removal Always Learnable? [56.28155520961125]
  Invariant learning can fail even when the structure is statistically identifiable.<n>We show a conditional computational barrier: under a black-box samplable supervised sparse recovery primitive, there exist emphamplable multi-dimensional environments.<n>Synthetic and real datasets illustrate the predicted gaps and transitions and motivate simple diversity diagnostics.
  arXiv  Detail & Related papers  (2026-06-11T05:49:43Z)
• Operator Spectroscopy of Trained Lattice Samplers [0.0]
  We analyze the trained field-space function itself.<n>We project these functions onto operator bases fixed before the fit.<n>The operator basis is model- and symmetry-dependent, but the test is common.
  arXiv  Detail & Related papers  (2026-05-11T20:06:15Z)
• Self-Normalized Martingales and Uniform Regret Bounds for Linear Regression [65.82017723631897]
  We show that scale-invariant upper bounds on self-normalized martingales are possible.<n>We derive a self-normalized concentration inequality free of the usual regularization penalties.
  arXiv  Detail & Related papers  (2026-05-02T22:39:00Z)
• Any-Subgroup Equivariant Networks via Symmetry Breaking [47.72921214239821]
  equivariant architectures are usually highly constrained, designed for symmetries chosen a priori.<n>This precludes the development of flexible, multi-modal foundation models capable of processing diverse data equivariantly.<n>We build a single model that can be simultaneously equivariant to several groups, simply by modulating a certain auxiliary input feature.
  arXiv  Detail & Related papers  (2026-03-19T21:30:41Z)
• Anisotropic local law for non-separable sample covariance matrices [10.181748307494608]
  We establish local laws for sample covariance matrices $K = N-1sum_i=1N g_ig_ig_i*$ where the random vectors $g_1, ldots, g_N in Rn$ are independent with common covariance $$.<n>We discuss several classes of non-separable examples satisfying our assumptions, including conditionally mean-zero distributions, the random features model $g = (Xw)$ arising in machine learning, and Gaussian measures with
  arXiv  Detail & Related papers  (2026-02-20T03:28:51Z)
• Rethinking Diffusion Models with Symmetries through Canonicalization with Applications to Molecular Graph Generation [56.361076943802594]
  CanonFlow achieves state-of-the-art performance on the challenging GEOM-DRUG dataset, and the advantage remains large in few-step generation.
  arXiv  Detail & Related papers  (2026-02-16T18:58:55Z)
• Unit-Consistent (UC) Adjoint for GSD and Backprop in Deep Learning Applications [0.0]
  We formulate the invariance requirement at the level of the backward adjoint/optimization geometry.<n>By replacing the Euclidean-level recipe, we derive a Unit-consistent gauge descent and backprogation.
  arXiv  Detail & Related papers  (2026-01-15T21:58:04Z)
• High-Rank Irreducible Cartesian Tensor Decomposition and Bases of Equivariant Spaces [48.465738895704455]
  We construct path matrices for decomposition of Cartesian tensors up to rank $n=9$ with reduced and affordable complexity.<n>Our method avoids the RREF algorithm and maintains a fully analytical derivation of each ICT decomposition matrix.<n>We extend our result to the arbitrary tensor product and direct sum spaces, enabling free design between different spaces while keeping symmetry.
  arXiv  Detail & Related papers  (2024-12-24T08:25:38Z)
• Quantum Random Walks and Quantum Oscillator in an Infinite-Dimensional Phase Space [45.9982965995401]
  We consider quantum random walks in an infinite-dimensional phase space constructed using Weyl representation of the coordinate and momentum operators. We find conditions for their strong continuity and establish properties of their generators.
  arXiv  Detail & Related papers  (2024-06-15T17:39:32Z)
• Geometry of Linear Neural Networks: Equivariance and Invariance under Permutation Groups [1.8434042562191815]
  We investigate the subvariety of functions that are equivariant or invariant under the action of a permutation group.<n>We draw conclusions for the parameterization and the design of equivariant and invariant linear networks.
  arXiv  Detail & Related papers  (2023-09-24T19:40:15Z)
• Integral Quantization for the Discrete Cylinder [0.456877715768796]
  We show how to derive corresponding covariant integral quantizations from (weight) functions on the phase space. We also look at the specific cases of coherent states built from shifted gaussians, Von Mises, Poisson, and Fej'er kernels.
  arXiv  Detail & Related papers  (2022-08-19T21:23:43Z)
• Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces [52.424621227687894]
  We introduce a unified framework for group equivariant networks on homogeneous spaces. We take advantage of the sparsity of Fourier coefficients of the lifted feature fields. We show that other methods treating features as the Fourier coefficients in the stabilizer subgroup are special cases of our activation.
  arXiv  Detail & Related papers  (2022-06-16T17:59:01Z)
• Coordinate Independent Convolutional Networks -- Isometry and Gauge Equivariant Convolutions on Riemannian Manifolds [70.32518963244466]
  A major complication in comparison to flat spaces is that it is unclear in which alignment a convolution kernel should be applied on a manifold. We argue that the particular choice of coordinatization should not affect a network's inference -- it should be coordinate independent. A simultaneous demand for coordinate independence and weight sharing is shown to result in a requirement on the network to be equivariant.
  arXiv  Detail & Related papers  (2021-06-10T19:54:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.