From Non-Convex Self-Concordant Regularization to Scalable Quasi-Newton Training of PINNs

• URL: http://arxiv.org/abs/2608.04206v1
• Date: Tue, 04 Aug 2026 20:05:21 GMT
• Title: From Non-Convex Self-Concordant Regularization to Scalable Quasi-Newton Training of PINNs
• Abstract summary: SCORE is a self-concordance-inspired quasi-Newton method with decrement-coupled shifted secant geometry for PINN training.<n>Its distinguishing mechanism is that a single quasi-Newton decrement computed from the learned inverse metric jointly determines a strong-Wolfe-tested candidate step.<n>Experiments on the Burgers, Kuramoto--Sivashinsky, Korteweg--de Vries, and complex Ginzburg--Landau equations show that SCORE attains lower final errors than the tested BFGS and self-scaled Broyden baselines.
• Score: 10.223108587188808
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Physics-informed neural networks (PINNs) often require high-accuracy quasi-Newton refinement to obtain reliable partial differential equation solutions, but their residual objectives can exhibit indefinite, nearly singular, and poorly scaled local curvature. Regularized quasi-Newton methods provide established mechanisms for stabilizing secant models, while self-concordant methods provide local-metric rules for curvature-dependent step selection. Building on these two lines of work, we propose SCORE, a self-concordance-inspired quasi-Newton method with decrement-coupled shifted secant geometry for PINN training. Its distinguishing mechanism is that a single quasi-Newton decrement computed from the learned inverse metric jointly determines a strong-Wolfe-tested candidate step and an adaptive shift used to define the next secant geometry. The shifted displacement represents the action of an averaged shifted metric along the accepted step, while requiring neither Hessian construction nor Hessian-vector products. Under a local spectral-equivalence condition, we show that the quasi-Newton decrement and candidate step remain comparable to their counterparts in a positive shifted metric, and recover the normalized self-concordant rule in the matched-metric case. Strong Wolfe acceptance, fallback line search, and standard curvature safeguards provide globalization without modifying the underlying PINN objective. Experiments on the viscous Burgers, Kuramoto--Sivashinsky, Korteweg--de Vries, and complex Ginzburg--Landau equations show that SCORE attains lower final errors than the tested BFGS and self-scaled Broyden baselines. The Burgers ablation further indicates that shifted curvature stabilization and decrement-based step selection make complementary contributions to high-accuracy refinement.

Related papers

• Scalable Lindblad Noise Learning via Stochastic Tensor-Network Simulation [48.887627688666974]
  Learning dissipation rates in large-scale open quantum systems is a major obstacle for near-term quantum technologies.<n>Here, we propose a scalable noise-learning framework for Lindblad dissipation rates that combines a simulation method, the Jump Method (TJM)<n>We demonstrate the approach on two noise models in the Ising model, in which independent dissipation rates are learned for each site up to $N_mathrmsite=16$.<n>This combination of scalable numerics and rigorous theoretical guarantees positions TJM-based noise learning as a practical foundation for characterizing dissipation in large quantum devices.
  arXiv  Detail & Related papers  (2026-08-25T15:07:11Z)
• Symplectic H2 Model Reduction for High-Dimensional Linear Quantum Systems [3.7887687619674413]
  A symplectic Petrov-Galerkin framework is presented, in which reduced-order models automatically satisfy the PR identities by construction.<n>A symplectic variant of the iterative rational Krylov algorithm is developed and referred to as Quantum IRKA (Q-IRKA)<n>Results show that Q-IRKA is effective for large-scale linear quantum systems.
  arXiv  Detail & Related papers  (2026-05-08T02:38:57Z)
• Stability and Generalization of Push-Sum Based Decentralized Optimization over Directed Graphs [55.77845440440496]
  Push-based decentralized communication enables optimization over communication networks, where information exchange may be asymmetric.<n>We develop a unified uniform-stability framework for the Gradient Push (SGP) algorithm.<n>A key technical ingredient is an imbalance-aware generalization bound through two quantities.
  arXiv  Detail & Related papers  (2026-02-24T05:32:03Z)
• Tighter Asymptotic Key Rates for Intensity-Correlated Decoy-State QKD via Nonlinear Programming [0.0]
  Real sources can exhibit correlated intensity drift across rounds, potentially leaking intensity information and breaking the standard decoy-state reduction to linear programs.<n>We propose a reproducible alternative: first solve the full parameter-estimation problems using the interior-point nonlinear IPOPT, then use the resulting candidate solution as the linearisation point for the outer solver that certifies a valid lower bound on the key rate.<n> Simulations for both coarse-grained model-independent correlations and fine-grained truncatedGaussian models show consistently tighter key-rate bounds than canonical reference points, and in some cases allow certifying optimality when both optimisation stages coincide.
  arXiv  Detail & Related papers  (2026-02-04T19:00:05Z)
• Breaking the Stochasticity Barrier: An Adaptive Variance-Reduced Method for Variational Inequalities [0.0]
  We propose VR-A-A (VarianceReduced-Ascent with Armijo) as a novel algorithm for non-con optimization tasks.<n>We show that our method effectively suppresses limit cycles and accelerates convergence with reduced dependence on manual learning scheduling.
  arXiv  Detail & Related papers  (2026-01-30T14:43:07Z)
• Probing the Ground State of the Antiferromagnetic Heisenberg Model on the Kagome Lattice using Geometrically Informed Variational Quantum Eigensolver [0.0]
  This work investigates the nature of the ground state of the antiferromagnetic Heisenberg model on minimal kagome cells.<n>We demonstrate that the ground state preparation is achievable using a shallow hardware-efficient quantum circuit.<n>We further apply error mitigation techniques, including zero noise Rayleigh (ZNE) and qubit-wise readout error mitigation (REM)
  arXiv  Detail & Related papers  (2025-09-22T17:02:58Z)
• Simple Stepsize for Quasi-Newton Methods with Global Convergence Guarantees [46.16377198030688]
  We extend the theoretical understanding of Quasi-Newton methods by introducing a simple stepsize schedule that guarantees a global convergence rate of $O (1/k)$ for the convex functions.<n>We show that when the inexactness of the Hessian approximation is controlled within a prescribed relative accuracy, the method attains an accelerated convergence rate of $O (1/k)$ -- matching the best-known rates of both Nesterov's accelerated gradient method and cubically regularized Newton methods.
  arXiv  Detail & Related papers  (2025-08-27T09:18:51Z)
• Euclidean Distance Matrix Completion via Asymmetric Projected Gradient Descent [25.846262685970164]
  This paper proposes and analyzes a gradient-type algorithm based on Burer-Monteiro factorization.<n>It reconstructs the point set configuration from partial Euclidean distance measurements.
  arXiv  Detail & Related papers  (2025-04-28T07:13:23Z)
• Stable Nonconvex-Nonconcave Training via Linear Interpolation [51.668052890249726]
  This paper presents a theoretical analysis of linearahead as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss landscape and show how linear can help by leveraging the theory of nonexpansive operators.
  arXiv  Detail & Related papers  (2023-10-20T12:45:12Z)
• Provably Accelerating Ill-Conditioned Low-rank Estimation via Scaled Gradient Descent, Even with Overparameterization [48.65416821017865]
  This chapter introduces a new algorithmic approach, dubbed scaled gradient (ScaledGD) It converges linearly at a constant rate independent of the condition number of the low-rank object. It maintains the low periteration cost of gradient descent for a variety of tasks.
  arXiv  Detail & Related papers  (2023-10-09T21:16:57Z)
• Error-Correcting Neural Networks for Two-Dimensional Curvature Computation in the Level-Set Method [0.0]
  We present an error-neural-modeling-based strategy for approximating two-dimensional curvature in the level-set method. Our main contribution is a redesigned hybrid solver that relies on numerical schemes to enable machine-learning operations on demand.
  arXiv  Detail & Related papers  (2022-01-22T05:14:40Z)
• On the Convergence of Stochastic Extragradient for Bilinear Games with Restarted Iteration Averaging [96.13485146617322]
  We present an analysis of the ExtraGradient (SEG) method with constant step size, and present variations of the method that yield favorable convergence. We prove that when augmented with averaging, SEG provably converges to the Nash equilibrium, and such a rate is provably accelerated by incorporating a scheduled restarting procedure.
  arXiv  Detail & Related papers  (2021-06-30T17:51:36Z)

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.