{
 "artifacts": null,
 "category": "dynamics",
 "description": "Regularize a recurrent or continuous-time state model according to the response residues of its slow Jacobian modes, rather than penalizing every small eigenvalue equally. A mode is penalized only when it is both dynamically slow and strongly coupled to the chosen output, loss, or input perturbation, preserving useful slow memory while suppressing dangerous amplification.",
 "formulas_latex": [
  "$$\\mathscr{R}_{j,k}^{f}(B)=\\mu\\!\\left(BN_j^k\\Pi_j f^c\\right),\\qquad f^c=f-\\mu(f)$$",
  "$$\\text{sensitivity contribution}_{j,k}\\;\\propto\\;\\frac{\\mathscr{R}_{j,k}^{f}(B)}{(-\\lambda_j)^{k+1}}$$",
  "$$Jr_j=\\lambda_jr_j,\\quad l_j^\\top J=\\lambda_jl_j^\\top,\\quad l_j^\\top r_j=1,\\quad \\Pi_j=r_jl_j^\\top$$",
  "$$\\mathcal{L}_{\\mathrm{res}}=\\frac{1}{|\\mathcal{S}|}\\sum_{j\\in\\mathcal{S}}\\left(\\frac{|\\widehat{R}_j|}{|\\lambda_j|+\\varepsilon}\\right)^2,\\qquad \\widehat{R}_j=\\frac{1}{N}\\sum_{i=1}^{N}b(h_i)^\\top\\Pi_j\\nabla_h f(h_i)$$"
 ],
 "id": 3071,
 "implementation": "Integrate this into the recurrent-state update or neural-ODE vector field, not into the classifier head. During each training interval, collect a minibatch of hidden states \\(h_i\\) and define \\(f(h)\\) as either the task loss contribution, a selected logit, or the scalar readout used by the downstream head. Choose \\(b(h)\\) as the derivative of the vector field with respect to a selected input coordinate, an input-noise direction, or a random Hutchinson direction in state space. Estimate the rightmost or smallest-magnitude eigenmodes of the local Jacobian \\(J_i=\\partial F_\\theta(h_i,x_i)/\\partial h_i\\) using Arnoldi; for a cheap MVP use one representative minibatch Jacobian or Jacobian-vector products averaged across the batch. Compute left vectors by Arnoldi on \\(J^\\top\\), normalize each pair so \\(l_j^\\top r_j=1\\), and form \\(\\Pi_j=r_jl_j^\\top\\). Estimate \\(\\widehat R_j\\) from the displayed empirical average. Add \\(\\alpha\\mathcal L_{\\mathrm{res}}\\) to the task loss, clipping the penalty to the slowest K modes and using stop-gradient through the eigensolver initially. Pseudocode: sample states; estimate JVP/VJP operators; run Arnoldi(J,K); pair left/right modes; compute \\(R_j\\leftarrow N^{-1}\\sum_i b_i^\\top r_jl_j^\\top\\nabla f_i\\); accumulate \\((|R_j|/(|\\lambda_j|+\\varepsilon))^2\\); backpropagate task loss plus penalty. The mathematical quantities are the projector-residue formula and inverse spectral denominator; empirical quantities are the Jacobian, eigenmodes, state measure, and perturbation directions. First test on a 1–2 layer continuous-time RNN or 64-dimensional neural ODE on sequential MNIST or permuted sequential CIFAR-10, against spectral-radius, Jacobian-norm, and no-regularizer baselines. Measure exploding gradients, sensitivity to injected input noise, long-horizon hidden-state stability, and validation accuracy at equal parameter count. Success is lower perturbation amplification and fewer unstable runs without destroying long-range-memory accuracy; a stronger result is equal accuracy with a larger stable integration step.",
 "math_summary": "The paper writes the RP response residue for spectral block j and nilpotent order k as \\(\\mathscr{R}_{j,k}^{f}(B)=\\mu(BN_j^k\\Pi_j f^c)\\), where \\(\\mu\\) is the invariant or empirical state measure, \\(f^c=f-\\mu(f)\\) is the centered observable, \\(B\\) is the generator perturbation, \\(\\Pi_j\\) is the spectral projector for eigenvalue \\(\\lambda_j\\), and \\(N_j\\) is the nilpotent part of the Jordan block. The corresponding sensitivity contribution is proportional to \\(\\mathscr{R}_{j,k}^{f}(B)(-\\lambda_j)^{-(k+1)}\\): small \\(|\\lambda_j|\\) permits amplification, while the residue determines whether it is actually excited. For a finite-dimensional neural ODE \\(\\dot h=F_\\theta(h,x)\\), use the local Jacobian \\(J=\\partial F_\\theta/\\partial h\\), right and left eigenvectors \\(Jr_j=\\lambda_jr_j\\), \\(l_j^\\top J=\\lambda_jl_j^\\top\\), normalized by \\(l_j^\\top r_j=1\\), and projector \\(\\Pi_j=r_jl_j^\\top\\). For an input perturbation vector field \\(b(h)\\), define \\((B\\phi)(h)=b(h)^\\top\\nabla_h\\phi(h)\\). For scalar readout \\(f(h)\\), estimate the empirical residue by \\(\\widehat{R}_j=\\frac{1}{N}\\sum_{i=1}^{N}b(h_i)^\\top\\Pi_j\\nabla_h f(h_i)\\). The diagonalizable first-order gain is \\(G_j=|\\widehat{R}_j|/(|\\lambda_j|+\\varepsilon)\\); for a Jordan block of size \\(m_j\\), include \\(\\sum_{k=0}^{m_j-1}|\\widehat{R}_{j,k}|/(|\\lambda_j|+\\varepsilon)^{k+1}\\).",
 "math_tags": [
  "dynamical-systems",
  "spectral-theory",
  "linear-algebra",
  "operator-theory"
 ],
 "ml_areas": [
  "rnn",
  "ssm",
  "training-dynamics",
  "regularization"
 ],
 "paper": {
  "arxiv_id": "2609.02614",
  "arxiv_url": "https://arxiv.org/abs/2609.02614",
  "summary_what_math_gives_to_ml": "The paper's transferable asset is a residue-resolved spectral sensitivity principle: a small relaxation eigenvalue creates large response only when the observable and perturbation direction actually couple to that spectral block. Projectors and nilpotent Jordan components explain amplification that eigenvalue-gap monitoring alone misses, including strong transient response from non-normal dynamics with a frozen spectrum. This suggests replacing crude spectral-radius or smallest-gap regularization in recurrent and continuous-time networks with a mode-selective penalty based on observable–perturbation residues. The most direct first target is a neural ODE or state-space model, where local Jacobian modes, input perturbations, and readout sensitivities can be estimated with Arnoldi or Schur methods.",
  "title": "Ruelle--Pollicott Theory for Metastable Systems: A Unified Framework for Tipping Transitions",
  "year": "2026"
 },
 "ratings": {
  "difficulty": 6,
  "novelty": 7,
  "usefulness": 6
 },
 "solves": [
  "stability",
  "generalization"
 ],
 "title": "Residue-aware Jacobian stabilization",
 "url": "https://synthcore.org/idea/3071/residue-aware-jacobian-stabilization",
 "verification": {
  "peer_reviewed": false,
  "status": "unverified",
  "status_label": "Unverified",
  "verdict_source": "deterministic test code (paired-seed permutation statistics)",
  "verification_axes": {
   "benchmark_mechanism": {
    "confirmed": null,
    "tested": false
   },
   "practical_benchmark": {
    "beats_baseline": null,
    "tested": false
   },
   "toy_mechanism_gate": {
    "confirmed": null,
    "tested": false
   }
  }
 }
}