A Nonlinear Separation Principle: Applications to Neural Networks, Control and Learning

• URL: http://arxiv.org/abs/2604.15238v1
• Date: Thu, 16 Apr 2026 17:12:32 GMT
• Title: A Nonlinear Separation Principle: Applications to Neural Networks, Control and Learning
• Abstract summary: This paper investigates continuous-time and discrete-time firing-rate and Hopfield recurrent neural networks (RNNs)<n>We introduce a nonlinear separation principle that guarantees global exponential stability for the interconnection of a contracting state-feedback controller and a contracting observer.<n>We derive sharp linear matrix inequality (LMI) conditions that guarantee the contractivity of both firing rate and Hopfield neural network architectures.
• Score: 3.2241707757984788
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper investigates continuous-time and discrete-time firing-rate and Hopfield recurrent neural networks (RNNs), with applications in nonlinear control design and implicit deep learning. First, we introduce a nonlinear separation principle that guarantees global exponential stability for the interconnection of a contracting state-feedback controller and a contracting observer, alongside parametric extensions for robustness and equilibrium tracking. Second, we derive sharp linear matrix inequality (LMI) conditions that guarantee the contractivity of both firing rate and Hopfield neural network architectures. We establish structural relationships among these certificates-demonstrating that continuous-time models with monotone non-decreasing activations maximize the admissible weight space, and extend these stability guarantees to interconnected systems and Graph RNNs. Third, we combine our separation principle and LMI framework to solve the output reference tracking problem for RNN-modeled plants. We provide LMI synthesis methods for feedback controllers and observers, and rigorously design a low-gain integral controller to eliminate steady-state error. Finally, we derive an exact, unconstrained algebraic parameterization of our contraction LMIs to design highly expressive implicit neural networks, achieving competitive accuracy and parameter efficiency on standard image classification benchmarks.

Related papers

• 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)
• Relaxation-Informed Training of Neural Network Surrogate Models [3.9722979176564763]
  ReLU neural networks trained surrogate models can be embedded exactly in mixed-integer linear programs (MILPs)<n>The tractability of the resulting MILP depends on structural properties of the network.<n>We show that the proposed regularizers can reduce MILP times by up to four orders of magnitude to an unregularized baseline.
  arXiv  Detail & Related papers  (2026-04-24T17:46:55Z)
• Differentiable Modeling for Low-Inertia Grids: Benchmarking PINNs, NODEs, and DP for Identification and Control of SMIB System [17.96236104895915]
  This paper presents a comparative study of different differentiable programming paradigms for modeling, identification, and control of power system dynamics.<n>We evaluate their performance in trajectory extrapolation, parameter estimation, and Linear Quadratic Regulator (LQR) synthesis.<n>Our results highlight a fundamental trade-off between data-driven flexibility and physical structure.
  arXiv  Detail & Related papers  (2026-02-10T11:22:59Z)
• Scaling up Stability: Reinforcement Learning for Distributed Control of Networked Systems in the Space of Stabilizing Policies [0.49109372384514843]
  We introduce a policy parameterization that embeds Graph Neural Networks (GNNs) into a Youla-like magnitude-direction parameterization.<n>The magnitude is implemented as a stable operator consisting of a GNN acting on disturbance feedback, while the direction is a GNN acting on local observations.<n>Experiments show that policies trained on small networks transfer directly to larger ones and unseen network topologies, achieve higher returns and lower variance than a state-of-the-art MARL baseline.
  arXiv  Detail & Related papers  (2025-12-20T23:35:07Z)
• Verifying Closed-Loop Contractivity of Learning-Based Controllers via Partitioning [52.23804865017831]
  We address the problem of verifying closed-loop contraction in nonlinear control systems whose controller and contraction metric are both parameterized by neural networks.<n>We derive a tractable and scalable sufficient condition for closed-loop contractivity that reduces to checking that the dominant eigenvalue of a symmetric Metzler matrix is nonpositive.
  arXiv  Detail & Related papers  (2025-12-01T23:06:56Z)
• Stable-by-Design Neural Network-Based LPV State-Space Models for System Identification [6.5745172279769255]
  We propose a neural network-based state-space model that simultaneously learns latent states and internal scheduling variables.<n>The state-transition matrix is guaranteed to be stable through a Schur-based parameterization.<n>The proposed NN-SS is evaluated on benchmark nonlinear systems, and the results demonstrate that the model consistently matches or surpasses classical subspace identification methods.
  arXiv  Detail & Related papers  (2025-10-21T10:25:54Z)
• Recurrent Stochastic Configuration Networks with Hybrid Regularization for Nonlinear Dynamics Modelling [3.8719670789415925]
  Recurrent configuration networks (RSCNs) have shown great potential in modelling nonlinear dynamic systems with uncertainties.<n>This paper presents an RSCN with hybrid regularization to enhance both the learning capacity and generalization performance of the network.
  arXiv  Detail & Related papers  (2024-11-26T03:06:39Z)
• Lyapunov-stable Neural Control for State and Output Feedback: A Novel Formulation [67.63756749551924]
  Learning-based neural network (NN) control policies have shown impressive empirical performance in a wide range of tasks in robotics and control. Lyapunov stability guarantees over the region-of-attraction (ROA) for NN controllers with nonlinear dynamical systems are challenging to obtain. We demonstrate a new framework for learning NN controllers together with Lyapunov certificates using fast empirical falsification and strategic regularizations.
  arXiv  Detail & Related papers  (2024-04-11T17:49:15Z)
• Benign Overfitting in Deep Neural Networks under Lazy Training [72.28294823115502]
  We show that when the data distribution is well-separated, DNNs can achieve Bayes-optimal test error for classification. Our results indicate that interpolating with smoother functions leads to better generalization.
  arXiv  Detail & Related papers  (2023-05-30T19:37:44Z)
• A Theoretical Overview of Neural Contraction Metrics for Learning-based Control with Guaranteed Stability [7.963506386866862]
  This paper presents a neural network model of an optimal contraction metric and corresponding differential Lyapunov function. Its innovation lies in providing formal robustness guarantees for learning-based control frameworks.
  arXiv  Detail & Related papers  (2021-10-02T00:28:49Z)
• Lipschitz Recurrent Neural Networks [100.72827570987992]
  We show that our Lipschitz recurrent unit is more robust with respect to input and parameter perturbations as compared to other continuous-time RNNs. Our experiments demonstrate that the Lipschitz RNN can outperform existing recurrent units on a range of benchmark tasks.
  arXiv  Detail & Related papers  (2020-06-22T08:44:52Z)
• Neural Control Variates [71.42768823631918]
  We show that a set of neural networks can face the challenge of finding a good approximation of the integrand. We derive a theoretically optimal, variance-minimizing loss function, and propose an alternative, composite loss for stable online training in practice. Specifically, we show that the learned light-field approximation is of sufficient quality for high-order bounces, allowing us to omit the error correction and thereby dramatically reduce the noise at the cost of negligible visible bias.
  arXiv  Detail & Related papers  (2020-06-02T11:17:55Z)
• Kernel and Rich Regimes in Overparametrized Models [69.40899443842443]
  We show that gradient descent on overparametrized multilayer networks can induce rich implicit biases that are not RKHS norms. We also demonstrate this transition empirically for more complex matrix factorization models and multilayer non-linear networks.
  arXiv  Detail & Related papers  (2020-02-20T15:43:02Z)

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.