Stability and Bifurcation Analysis of Nonlinear PDEs via Random Projection-based PINNs: A Krylov-Arnoldi Approach

• URL: http://arxiv.org/abs/2603.21568v1
• Date: Mon, 23 Mar 2026 04:41:10 GMT
• Title: Stability and Bifurcation Analysis of Nonlinear PDEs via Random Projection-based PINNs: A Krylov-Arnoldi Approach
• Abstract summary: We address the stability and bifurcation analysis of nonlinear partial differential equations (PDEs) in which the solution is sought in the function space spanned by physics-informed random projection neural networks (PI-RPNNs)<n>We introduce a matrix-free shift-invert Krylov-Arnoldi method that operates directly in weight space, avoiding explicit inversion of the numerically rank-deficient collocation matrix.<n>We prove that the PI-RPNN-based generalized eigenvalue problem is almost surely regular, guaranteeing solvability with standard eigensolvers.
• Score: 1.4174475093445233
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We address a numerical framework for the stability and bifurcation analysis of nonlinear partial differential equations (PDEs) in which the solution is sought in the function space spanned by physics-informed random projection neural networks (PI-RPNNs), and discretized via a collocation approach. These are single-hidden-layer networks with randomly sampled and fixed a priori hidden-layer weights; only the linear output layer weights are optimized, reducing training to a single least-squares solve. This linear output structure enables the direct and explicit formulation of the eigenvalue problem governing the linear stability of stationary solutions. This takes a generalized eigenvalue form, which naturally separates the physical domain interior dynamics from the algebraic constraints imposed by boundary conditions, at no additional training cost and without requiring additional PDE solves. However, the random projection collocation matrix is inherently numerically rank-deficient, rendering naive eigenvalue computation unreliable and contaminating the true eigenvalue spectrum with spurious near-zero modes. To overcome this limitation, we introduce a matrix-free shift-invert Krylov-Arnoldi method that operates directly in weight space, avoiding explicit inversion of the numerically rank-deficient collocation matrix and enabling the reliable computation of several leading eigenpairs of the physical Jacobian - the discretized Frechet derivative of the PDE operator with respect to the solution field, whose eigenvalue spectrum determines linear stability. We further prove that the PI-RPNN-based generalized eigenvalue problem is almost surely regular, guaranteeing solvability with standard eigensolvers, and that the singular values of the random projection collocation matrix decay exponentially for analytic activation functions.

Related papers

• Linearized PINN with pretrained nonlinear layers [48.01541150431857]
  lPINN is a reduced-order neural basis method for forward and inverse differential equations.<n>We evaluate lPINN on forward and inverse problems for the advection-diffusion equation, Burgers' equation, and the nonlinear pendulum equation.
  arXiv  Detail & Related papers  (2026-09-14T02:18:00Z)
• Interpretable Activation-Selection Neural Networks for Symbolic Regression of Parameter-Dependent Hamiltonian Eigenvalues [45.88028371034407]
  We introduce an activation-selection network (ASN), a differentiable symbolic-regression architecture.<n>Each input node learns a sparse combination of predefined analytical functions, and the trained network can be converted directly into an explicit expression.<n>We apply the ASN to effective three- and four-site spin-chain Hamiltonians relevant to zero-quantum nuclear magnetic resonance.
  arXiv  Detail & Related papers  (2026-08-26T07:45:10Z)
• A Convex Quasilinearization Method for Solving Nonlinear PDEs with Physics-Informed Neural Networks [0.0]
  We present a numerical method for the forward solution of nonlinear partial differential equations (PDEs)<n>The method, LiL-Q, is assessed on seven benchmarks, including systems (planestrain elasticity and the incompressible Navier-Stokes equations in two and three dimensions) and steady flow with heterogeneous permeability.
  arXiv  Detail & Related papers  (2026-06-16T17:09:59Z)
• Adjoint Method versus Physics-Informed Neural Networks in PDE-Constrained Inverse Problems [48.470700002941136]
  Inverse problems governed by partial differential equations (PDEs) are central to computational mechanics and are commonly solved by adjoint-based optimization.<n> physics-informed neural networks (PINNs) have emerged as a flexible alternative.<n>We present a fair comparison of adjoint optimization and PINNs for PDE-constrained inverse problems.
  arXiv  Detail & Related papers  (2026-06-10T17:07:09Z)
• Eigen-Spike Emergence and Quadratic Equivalents for Conjugate Kernels on Nonlinearly Separable Data [41.325451060228126]
  We consider the conjugate kernel (CK), which is the nonlinear feature map of a feedforward NN, under a canonical nonlinearly separable dataset.<n>We develop a robust quadratic equivalent to the spiked CK matrix that enables a precise analysis of emergent informative spikes.<n>We derive a precise BBP-type phase transition in which linear classification via the CK eigenvectors becomes possible.
  arXiv  Detail & Related papers  (2026-05-28T09:32:19Z)
• Randomized Atomic Feature Models for Physics-Informed Identification of Dynamic Systems [3.810612452609132]
  We present a framework for system identification based on randomized stable atomic features.<n>The framework encodes stability margins, modal localization, DC-gain bounds, monotonicity, passivity, relative degree, settling-time targets, and time/frequency-domain error bounds.
  arXiv  Detail & Related papers  (2026-05-14T04:25:07Z)
• Randomized Neural Networks for Integro-Differential Equations with Application to Neutron Transport [10.653981193573676]
  In work, we present randomized neural networks (RaNNs) as a simulation of integrodifferential equations.<n>Because the RaNN is intrinsically dense globally supported random approximation, the nonlocal integral operator does not introduce an additional loss of sparsity.
  arXiv  Detail & Related papers  (2026-04-15T13:05:28Z)
• Adaptive-Growth Randomized Neural Networks for Level-Set Computation of Multivalued Nonlinear First-Order PDEs with Hyperbolic Characteristics [38.23142730599331]
  This paper proposes an Adaptive-Growth Randomized Neural Network (AG-RaNN) method for computing multivalued solutions of nonlinear first-order PDEs with hyperbolic characteristics.<n>Such solutions arise in geometric optics, seismic waves, semiclassical limit of quantum dynamics and high frequency limit of linear waves.
  arXiv  Detail & Related papers  (2026-03-01T13:16:25Z)
• Deep Deterministic Nonlinear ICA via Total Correlation Minimization with Matrix-Based Entropy Functional [41.05541240448253]
  Blind source separation, particularly through independent component analysis (ICA), is widely utilized across various signal processing domains.<n>We present deep deterministic nonlinear independent component analysis (DDICA), a novel deep neural network-based framework designed to address these limitations.<n>We validated DDICA across a range of applications, including simulated signal mixtures, hyperspectral image unmixing, modeling of primary visual receptive fields, and resting-state functional magnetic resonance imaging (fMRI) data analysis.
  arXiv  Detail & Related papers  (2025-12-31T19:44:19Z)
• Non-Asymptotic Stability and Consistency Guarantees for Physics-Informed Neural Networks via Coercive Operator Analysis [0.0]
  We present a unified theoretical framework for analyzing the stability and consistency of Physics-Informed Neural Networks (PINNs)<n>PINNs approximate solutions to partial differential equations (PDEs) by minimizing residual losses over sampled collocation and boundary points.<n>We formalize both operator-level and variational notions of consistency, proving that residual minimization in Sobolev norms leads to convergence in energy and uniform norms under mild regularity.
  arXiv  Detail & Related papers  (2025-06-16T14:41:15Z)
• Solving engineering eigenvalue problems with neural networks using the Rayleigh quotient [0.0]
  We show that a neural network discretization of the eigenfunction offers unique advantages for handling continuous eigenvalue problems.<n>We also discuss the utility of harmonic functions as a spectral basis for approximating solutions to partial differential equations.
  arXiv  Detail & Related papers  (2025-06-04T18:45:27Z)
• Probabilistic Exponential Integrators [36.98314810594263]
  Like standard solvers, they suffer performance penalties for certain stiff systems. This paper develops a class of probabilistic exponential solvers with favorable properties. We evaluate the proposed methods on multiple stiff differential equations.
  arXiv  Detail & Related papers  (2023-05-24T10:13:13Z)
• Stochastic Nonlinear Control via Finite-dimensional Spectral Dynamic Embedding [20.43835169613882]
  This paper proposes an approach, Spectral Dynamics Embedding Control (SDEC), to optimal control for nonlinear systems.<n>It reveals an infinite-dimensional feature representation induced by the system's nonlinear dynamics, enabling a linear representation of the state-action value function.<n>For practical implementation, this representation is approximated using finite-dimensional truncations.
  arXiv  Detail & Related papers  (2023-04-08T04:23:46Z)
• Analysis of the Single Reference Coupled Cluster Method for Electronic Structure Calculations: The Full Coupled Cluster Equations [2.3271703838711972]
  We introduce a new well-posedness analysis for the single reference coupled cluster method based on the invertibility of the CC derivative. Preliminary numerical experiments indicate that the constants that appear in our estimates are a significant improvement over those obtained from the local monotonicity approach.
  arXiv  Detail & Related papers  (2022-12-24T17:29:43Z)
• Physics-Informed Gaussian Process Regression Generalizes Linear PDE Solvers [32.57938108395521]
  A class of mechanistic models, Linear partial differential equations, are used to describe physical processes such as heat transfer, electromagnetism, and wave propagation. specialized numerical methods based on discretization are used to solve PDEs. By ignoring parameter and measurement uncertainty, classical PDE solvers may fail to produce consistent estimates of their inherent approximation error.
  arXiv  Detail & Related papers  (2022-12-23T17:02:59Z)
• Message Passing Neural PDE Solvers [60.77761603258397]
  We build a neural message passing solver, replacing allally designed components in the graph with backprop-optimized neural function approximators. We show that neural message passing solvers representationally contain some classical methods, such as finite differences, finite volumes, and WENO schemes. We validate our method on various fluid-like flow problems, demonstrating fast, stable, and accurate performance across different domain topologies, equation parameters, discretizations, etc., in 1D and 2D.
  arXiv  Detail & Related papers  (2022-02-07T17:47:46Z)

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.