Related papers: Lyapunov-Net: A Deep Neural Network Architecture for Lyapunov Function Approximation

Lyapunov-Net: A Deep Neural Network Architecture for Lyapunov Function Approximation

URL: http://arxiv.org/abs/2109.13359v1
Date: Mon, 27 Sep 2021 21:42:19 GMT
Title: Lyapunov-Net: A Deep Neural Network Architecture for Lyapunov Function Approximation
Authors: Nathan Gaby and Fumin Zhang and Xiaojing Ye
Abstract summary: We develop a versatile deep neural network architecture, called Lyapunov-Net, to approximate Lyapunov functions in high dimensions. Lyapunov-Net guarantees positive definiteness, and thus it can be easily trained to satisfy the negative orbital derivative condition.
Score: 7.469944784454579
License: http://creativecommons.org/licenses/by/4.0/
Abstract: We develop a versatile deep neural network architecture, called Lyapunov-Net, to approximate Lyapunov functions of dynamical systems in high dimensions. Lyapunov-Net guarantees positive definiteness, and thus it can be easily trained to satisfy the negative orbital derivative condition, which only renders a single term in the empirical risk function in practice. This significantly reduces the number of hyper-parameters compared to existing methods. We also provide theoretical justifications on the approximation power of Lyapunov-Net and its complexity bounds. We demonstrate the efficiency of the proposed method on nonlinear dynamical systems involving up to 30-dimensional state spaces, and show that the proposed approach significantly outperforms the state-of-the-art methods.

Related papers

Learning and Verifying Maximal Taylor-Neural Lyapunov functions [0.4910937238451484]
We introduce a novel neural network architecture, termed Taylor-neural Lyapunov functions. This architecture encodes local approximations and extends them globally by leveraging neural networks to approximate the residuals. This work represents a significant advancement in control theory, with broad potential applications in the design of stable control systems and beyond.
arXiv Detail & Related papers (2024-08-30T12:40:12Z)
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)
Hallmarks of Optimization Trajectories in Neural Networks: Directional Exploration and Redundancy [75.15685966213832]
We analyze the rich directional structure of optimization trajectories represented by their pointwise parameters. We show that training only scalar batchnorm parameters some while into training matches the performance of training the entire network.
arXiv Detail & Related papers (2024-03-12T07:32:47Z)
Learning Active Subspaces for Effective and Scalable Uncertainty Quantification in Deep Neural Networks [13.388835540131508]
We propose a novel scheme for constructing a low-dimensional subspace of the neural network parameters. We demonstrate that the significantly reduced active subspace enables effective and scalable Bayesian inference. Our approach provides reliable predictions with robust uncertainty estimates for various regression tasks.
arXiv Detail & Related papers (2023-09-06T15:00:36Z)
Guaranteed Conservation of Momentum for Learning Particle-based Fluid Dynamics [96.9177297872723]
We present a novel method for guaranteeing linear momentum in learned physics simulations. We enforce conservation of momentum with a hard constraint, which we realize via antisymmetrical continuous convolutional layers. In combination, the proposed method allows us to increase the physical accuracy of the learned simulator substantially.
arXiv Detail & Related papers (2022-10-12T09:12:59Z)
LyaNet: A Lyapunov Framework for Training Neural ODEs [59.73633363494646]
We propose a method for training ordinary differential equations by using a control-theoretic Lyapunov condition for stability. Our approach, called LyaNet, is based on a novel Lyapunov loss formulation that encourages the inference dynamics to converge quickly to the correct prediction.
arXiv Detail & Related papers (2022-02-05T10:13:14Z)
Efficiently Solving High-Order and Nonlinear ODEs with Rational Fraction Polynomial: the Ratio Net [3.155317790896023]
This study takes a different approach by introducing neural network architecture for constructing trial functions, known as ratio net. Through empirical trials, it demonstrated that the proposed method exhibits higher efficiency compared to existing approaches. The ratio net holds promise for advancing the efficiency and effectiveness of solving differential equations.
arXiv Detail & Related papers (2021-05-18T16:59:52Z)
Formal Synthesis of Lyapunov Neural Networks [61.79595926825511]
We propose an automatic and formally sound method for synthesising Lyapunov functions. We employ a counterexample-guided approach where a numerical learner and a symbolic verifier interact to construct provably correct Lyapunov neural networks. Our method synthesises Lyapunov functions faster and over wider spatial domains than the alternatives, yet providing stronger or equal guarantees.
arXiv Detail & Related papers (2020-03-19T17:21:02Z)
Neural Proximal/Trust Region Policy Optimization Attains Globally Optimal Policy [119.12515258771302]
We show that a variant of PPOO equipped with over-parametrization converges to globally optimal networks. The key to our analysis is the iterate of infinite gradient under a notion of one-dimensional monotonicity, where the gradient and are instant by networks.
arXiv Detail & Related papers (2019-06-25T03:20:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.