Coercivity and Local Convergence of Physical Learning in Linear Circuits

• URL: http://arxiv.org/abs/2606.15443v1
• Date: Sat, 13 Jun 2026 19:18:51 GMT
• Title: Coercivity and Local Convergence of Physical Learning in Linear Circuits
• Abstract summary: Physical learning methods train physical networks to perform computational tasks using only local update rules.<n>We provide the first local convergence analysis of three such methods.<n>We show that coercivity can fail by exhibiting a kite circuit in which a symmetry causes the coercivity constant to degenerate.
• Score: 0.25489046505746704
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Physical learning methods train physical networks to perform computational tasks using only local update rules, exploiting the physics of the system to handle the global transfer of information. We provide the first local convergence analysis of three such methods -- Equilibrium Propagation (EP), Coupled Learning (CL), and a new method we call Adjoint Coupled Learning (AL) -- for linear circuits, in the limit of small-nudging for both discrete and continuous time. EP and AL perform gradient descent on a natural loss function, while CL follows modified dynamics with an additional cubic correction. Assuming the existence of a solution, we identify a coercivity condition, expressed as a rank condition on a matrix built from the network's incidence structure, under which the training loss decays exponentially and the parameters converge to the solution manifold. We show that coercivity can fail by exhibiting a kite circuit in which a symmetry causes the coercivity constant to degenerate on the solution manifold, but prove using Sard's theorem that such degeneracies are non-generic: coercivity holds at every point of the solution manifold for almost every choice of desired output.

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)
• Effective Covariance Dynamics in Solvable High-Dimensional GANs [2.639628765667673]
  We study a solvable high-dimensional model of generative adversarial network (GAN) training in which a linear generator learns a low-dimensional subspace from data.<n>We prove that the microscopic training process converges, in the high-dimensional limit, to deterministic ordinary differential equations governed by this effective covariance.
  arXiv  Detail & Related papers  (2026-06-25T16:33:54Z)
• 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)
• 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)
• Continuous-Time Dynamics of the Difference-of-Convex Algorithm [0.0]
  We induce the continuous-time structure of the difference-of-generate (DCA) for smooth DC decompositions with a convex component.<n>We show that different DC decompositions of the same objective link different continuous dynamics.
  arXiv  Detail & Related papers  (2026-04-08T10:38:07Z)
• ODELoRA: Training Low-Rank Adaptation by Solving Ordinary Differential Equations [54.886931928255564]
  Low-rank adaptation (LoRA) has emerged as a widely adopted parameter-efficient fine-tuning method in deep transfer learning.<n>We propose a novel continuous-time optimization dynamic for LoRA factor matrices in the form of an ordinary differential equation (ODE)<n>We show that ODELoRA achieves stable feature learning, a property that is crucial for training deep neural networks at different scales of problem dimensionality.
  arXiv  Detail & Related papers  (2026-02-07T10:19:36Z)
• 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)
• Learning Discretized Neural Networks under Ricci Flow [48.47315844022283]
  We study Discretized Neural Networks (DNNs) composed of low-precision weights and activations.<n>DNNs suffer from either infinite or zero gradients due to the non-differentiable discrete function during training.
  arXiv  Detail & Related papers  (2023-02-07T10:51:53Z)
• 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)
• 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)
• Mean-field Analysis of Piecewise Linear Solutions for Wide ReLU Networks [83.58049517083138]
  We consider a two-layer ReLU network trained via gradient descent. We show that SGD is biased towards a simple solution. We also provide empirical evidence that knots at locations distinct from the data points might occur.
  arXiv  Detail & Related papers  (2021-11-03T15:14:20Z)
• Deep Learning Approximation of Diffeomorphisms via Linear-Control Systems [91.3755431537592]
  We consider a control system of the form $dot x = sum_i=1lF_i(x)u_i$, with linear dependence in the controls. We use the corresponding flow to approximate the action of a diffeomorphism on a compact ensemble of points.
  arXiv  Detail & Related papers  (2021-10-24T08:57:46Z)
• Least-Squares Neural Network (LSNN) Method For Scalar Nonlinear Hyperbolic Conservation Laws: Discrete Divergence Operator [4.3226069572849966]
  A least-squares neural network (LSNN) method was introduced for solving scalar linear hyperbolic conservation laws. This paper rewrites HCLs in their divergence form of space time time introduces a new discrete divergence operator.
  arXiv  Detail & Related papers  (2021-10-21T04:50:57Z)

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.