A Convex Quasilinearization Method for Solving Nonlinear PDEs with Physics-Informed Neural Networks

• URL: http://arxiv.org/abs/2606.18175v1
• Date: Tue, 16 Jun 2026 17:09:59 GMT
• Title: A Convex Quasilinearization Method for Solving Nonlinear PDEs with Physics-Informed Neural Networks
• Abstract summary: 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.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a numerical method for the forward solution of nonlinear partial differential equations (PDEs) in which Bellman-Kalaba quasilinearization reduces the nonlinear problem to a sequence of linear subproblems, each discretized by collocation onto a trial space that is linear in its parameters and solved by a single direct linear least-squares QR factorization. The trial space, which we term Linear-in-Learnables (LiL), comprises representations whose trainable parameters enter linearly, including random-feature extreme learning machines, spectral polynomial bases, and trigonometric expansions, each implemented as a physics-informed neural network. The method thus replaces the nonconvex gradient-based training that limits standard PINNs with a convex per-step solve. We establish local Newton-Kantorovich convergence of the outer iteration to a residual-limited neighborhood under an explicit smallness condition, with the limiting accuracy governed by the best-approximation residual of the trial space rather than by an optimization tolerance. The method, denoted LiL-Q, is assessed on seven benchmarks spanning scalar nonlinear PDEs (Bratu, viscous Burgers, Buckley-Leverett), coupled systems (plane-strain elasticity and the incompressible Navier-Stokes equations in two and three spatial dimensions), and steady-state Darcy flow with heterogeneous permeability. Across these problems, LiL-Q converges in single-digit outer iterations in most cases, even at the coarsest basis sizes and independent of the parameter count. When the exact solution lies in the span of the trial space, the method recovers it to machine precision in a single solve. On the Navier-Stokes benchmarks, it matches or exceeds published PINN solvers with up to two orders of magnitude fewer trainable parameters, without gradient-based optimization.

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)
• Hybrid Iterative Neural Low-Regularity Integrator for Nonlinear Dispersive Equations [0.0]
  HIN-LRI is a hybrid framework that augments a classical numerical solver with a neural operator trained to correct the solver's structured truncation error.<n>A lightweight neural network, operating on a low-dimensional latent manifold, learns the residual defect that analytical methods cannot close.<n>Experiments show that HIN-LRI improves accuracy over analytical, splitting methods, and neural PDE surrogates, with stable spatial refinement, effective out-of-distribution transfer, and modest online overhead.
  arXiv  Detail & Related papers  (2026-05-06T12:50:36Z)
• Chebyshev-Augmented One-Shot Transfer Learning for PINNs on Nonlinear Differential Equations [0.794957965474334]
  Physics-Informed Neural Networks (PINNs) offer a flexible paradigm for solving differential equations by governing governing laws into the network.<n>A limitation is instance specificity: standard PINNs typically require retraining for each new forcing term, latent/initial condition, or nonlinear problems closed-form adaptation.<n>In this paper we address the class of nonlinearities amenable to one-shot PINN transfer by combining OTL with Chebyshev surrogates.
  arXiv  Detail & Related papers  (2026-05-02T22:49:37Z)
• 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)
• Online Inference of Constrained Optimization: Primal-Dual Optimality and Sequential Quadratic Programming [55.848340925419286]
  We study online statistical inference for the solutions of quadratic optimization problems with equality and inequality constraints.<n>We develop a sequential programming (SSQP) method to solve these problems, where the step direction is computed by sequentially performing an approximation of the objective and a linear approximation of the constraints.<n>We show that our method global almost moving-average convergence and exhibits local normality with an optimal primal-dual limiting matrix in the sense of Hjek and Le Cam.
  arXiv  Detail & Related papers  (2025-11-27T06:16:17Z)
• Explicit Discovery of Nonlinear Symmetries from Dynamic Data [50.20526548924647]
  LieNLSD is the first method capable of determining the number of infinitesimal generators with nonlinear terms and their explicit expressions.<n>LieNLSD shows qualitative advantages over existing methods and improves the long rollout accuracy of neural PDE solvers by over 20%.
  arXiv  Detail & Related papers  (2025-10-02T09:54:08Z)
• An N-Point Linear Solver for Line and Motion Estimation with Event Cameras [45.67822962085412]
  Event cameras respond primarily to edges--formed by strong gradients--that are well-suited for motion estimation. Recent work has shown that events generated by single lines satisfy a novel constraint which describes a manifold in space-time volume. We show that, with suitable line parametrization, this system of constraints is actually linear in the unknowns.
  arXiv  Detail & Related papers  (2024-04-01T00:47:02Z)
• Constrained Optimization via Exact Augmented Lagrangian and Randomized Iterative Sketching [55.28394191394675]
  We develop an adaptive inexact Newton method for equality-constrained nonlinear, nonIBS optimization problems. We demonstrate the superior performance of our method on benchmark nonlinear problems, constrained logistic regression with data from LVM, and a PDE-constrained problem.
  arXiv  Detail & Related papers  (2023-05-28T06:33:37Z)
• Numerical Approximation of Partial Differential Equations by a Variable Projection Method with Artificial Neural Networks [0.0]
  We present a method for solving linear and nonlinear PDEs based on the variable projection (VarPro) framework and artificial neural networks (ANNs) For linear PDEs, enforcing the boundary/initial value problem on the collocation points leads to a separable nonlinear least squares problem about the network coefficients. We reformulate this problem by the VarPro approach to eliminate the linear output-layer coefficients, leading to a reduced problem about the hidden-layer coefficients only.
  arXiv  Detail & Related papers  (2022-01-24T22:31:38Z)
• Solving and Learning Nonlinear PDEs with Gaussian Processes [11.09729362243947]
  We introduce a simple, rigorous, and unified framework for solving nonlinear partial differential equations. The proposed approach provides a natural generalization of collocation kernel methods to nonlinear PDEs and IPs. For IPs, while the traditional approach has been to iterate between the identifications of parameters in the PDE and the numerical approximation of its solution, our algorithm tackles both simultaneously.
  arXiv  Detail & Related papers  (2021-03-24T03:16:08Z)
• Optimal oracle inequalities for solving projected fixed-point equations [53.31620399640334]
  We study methods that use a collection of random observations to compute approximate solutions by searching over a known low-dimensional subspace of the Hilbert space. We show how our results precisely characterize the error of a class of temporal difference learning methods for the policy evaluation problem with linear function approximation.
  arXiv  Detail & Related papers  (2020-12-09T20:19:32Z)
• Convex Geometry and Duality of Over-parameterized Neural Networks [70.15611146583068]
  We develop a convex analytic approach to analyze finite width two-layer ReLU networks. We show that an optimal solution to the regularized training problem can be characterized as extreme points of a convex set. In higher dimensions, we show that the training problem can be cast as a finite dimensional convex problem with infinitely many constraints.
  arXiv  Detail & Related papers  (2020-02-25T23:05:33Z)

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.