{
 "artifacts": null,
 "category": "architecture",
 "description": "Build a neural operator that maps both a function-valued plant description and the current state trajectory to an action, while explicitly controlling sensitivity to each input. This should improve interpolation to unseen dynamics and prevent large action changes caused by small state or plant-estimation errors.",
 "formulas_latex": [
  "$$F[u](x,t)=\\sum_{n=2}^{\\infty}\\int_{T_n(x)}f_n(x,\\xi_1,\\ldots,\\xi_n)\\prod_{i=1}^{n}u(\\xi_i,t)\\,d\\xi_n\\cdots d\\xi_1,$$",
  "$$\\left|\\mathcal{U}_{N}(\\mathbf{f}_{N},u)-\\mathcal{U}_{N}(\\tilde{\\mathbf{f}}_{N},\\tilde{u})\\right|\\leq M_{N}(R)\\|\\mathbf{f}_{N}-\\tilde{\\mathbf{f}}_{N}\\|_{\\star}+M^{\\prime}_{N}(R)\\|u-\\tilde{u}\\|_{L^{\\infty}(0,1)},$$",
  "$$M_{N}(R)=\\sum_{n=2}^{N}\\frac{R^{n}}{n!}\\lambda_{n},\\qquad M^{\\prime}_{N}(R)=\\sum_{n=2}^{N}\\frac{nR^{n-1}}{n!}\\kappa_{n}.$$",
  "$$\\left|\\widehat{\\mathcal U}_{N}(\\mathbf f_N,u)-\\widehat{\\mathcal U}_{N}(\\tilde{\\mathbf f}_N,\\tilde u)\\right|\\leq L_f\\|\\mathbf f_N-\\tilde{\\mathbf f}_N\\|_{\\star}+L_u\\|u-\\tilde u\\|_{\\infty},\\quad L_f\\approx M_N(R),\\quad L_u\\approx M'_N(R).$$"
 ],
 "id": 265,
 "implementation": "Integrate this at the policy or transition-model head. Represent each coefficient function \\(f_n\\) on a fixed spatial grid or basis, encode the concatenated coefficient fields with a branch network, encode the sampled state trajectory \\(u(x_j)\\) with a second branch network or Fourier neural operator, and combine the two embeddings through a DeepONet-style bilinear head to produce the scalar action or boundary control. During each minibatch, create pairs \\((\\mathbf f,u)\\) and \\((\\tilde{\\mathbf f},\\tilde u)\\) by perturbing coefficients and states within known radii. Compute \\(d_f=\\|\\mathbf f-\\tilde{\\mathbf f}\\|_{\\star}\\) and \\(d_u=\\|u-\\tilde u\\|_\\infty\\), then add the penalty \\(\\max(0,|\\hat U-\\hat U'|-L_fd_f-L_ud_u)^2\\) to the ordinary imitation or prediction loss. Use spectral normalization in the branch and trunk layers, or estimate local gains with Jacobian-vector products. The paper's exact quantities are \\(M_N(R)\\) and \\(M'_N(R)\\); in a generic network, estimate \\(\\lambda_n\\) and \\(\\kappa_n\\) from perturbation slopes over training samples. First test on Burgers-like 1D systems with quadratic and cubic kernel nonlinearities, comparing an unconstrained MLP or FNO against this conditioned operator at equal parameter count. Measure action sensitivity under 1%, 5%, and 10% plant/state perturbations, held-out-plant prediction error, and closed-loop rollout failure rate. Success means lower worst-case action amplification and better stability without sacrificing nominal control cost.",
 "math_summary": "Theorem 1 states that the truncated controller operator \\(\\mathcal{U}_{N}\\) satisfies \\(|\\mathcal{U}_{N}(\\mathbf{f}_{N},u)-\\mathcal{U}_{N}(\\tilde{\\mathbf{f}}_{N},\\tilde u)|\\le M_{N}(R)\\|\\mathbf{f}_{N}-\\tilde{\\mathbf{f}}_{N}\\|_{\\star}+M'_N(R)\\|u-\\tilde u\\|_{L^{\\infty}(0,1)}\\). Here \\(\\mathbf f_N=(f_2,\\ldots,f_N)\\) is the collection of plant nonlinearity kernels, \\(u\\) is the state function on \\([0,1]\\), \\(R\\) bounds the state magnitude, \\(\\|\\cdot\\|_{\\star}\\) is the paper's kernel-coefficient norm, and \\(M_N(R)=\\sum_{n=2}^{N}R^n\\lambda_n/n!\\), \\(M'_N(R)=\\sum_{n=2}^{N}nR^{n-1}\\kappa_n/n!\\). The constants \\(\\lambda_n\\) and \\(\\kappa_n\\) bound the nth-order controller contribution with respect to plant kernels and state, respectively. The transferable property is separate, explicit sensitivity accounting for plant uncertainty and state perturbations.",
 "math_tags": [
  "functional-analysis",
  "approximation-theory",
  "pde",
  "dynamical-systems"
 ],
 "ml_areas": [
  "world-model",
  "ssm",
  "rl"
 ],
 "paper": {
  "arxiv_id": "2607.04362",
  "arxiv_url": "https://arxiv.org/abs/2607.04362",
  "summary_what_math_gives_to_ml": "The paper provides a useful recipe for replacing an expensive structured operator with a learned operator while retaining explicit robustness guarantees. Its transferable asset is not merely neural-operator approximation, but the joint Lipschitz bound in both the plant description and the state, together with a small-gain condition that converts uniform approximation error into a linear practical-stability radius. A strong ML adaptation is a plant-conditioned controller or simulator whose coefficient encoder and state encoder are trained and regularized to preserve these sensitivities, rather than treating the operator as an unconstrained black box. The most credible experiments are on families of low-dimensional nonlinear dynamical systems or PDE surrogates, measuring both interpolation and generalization across plant coefficients and closed-loop degradation under approximation error.",
  "title": "Approximate Feedback Linearization for a Nonlinear Hyperbolic PDE Class -- Part II: Neural Operator",
  "year": "2026"
 },
 "ratings": {
  "difficulty": 5,
  "novelty": 6,
  "usefulness": 7
 },
 "solves": [
  "stability",
  "generalization",
  "accuracy"
 ],
 "title": "Jointly Lipschitz plant-conditioned operator",
 "url": "https://synthcore.org/idea/265/jointly-lipschitz-plant-conditioned-operator",
 "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
   }
  }
 }
}