Neural network methods for Neumann series problems of Perron-Frobenius operators

Abstract

Problems related to Perron-Frobenius operators (or transfer operators) have been extensively studied and applied across various fields. In this work, we propose neural network methods for approximating solutions to problems involving these operators. Specifically, we focus on computing the power series of non-expansive Perron-Frobenius operators under a given $L^p$-norm with a constant damping parameter in $(0,1)$. We use PINNs and RVPINNs to approximate solutions in their strong and variational forms, respectively. We provide a priori error estimates for quasi-minimizers of the associated loss functions. We present some numerical results for 1D and 2D examples to show the performance of our methods. We also demonstrate the applicability of our methods by approximating interior densities in a two-cavity system.

References in corpus (18)

• DGM: A deep learning algorithm for solving partial differential equations
• Deep learning for universal linear embeddings of nonlinear dynamics
• hp-VPINNs: Variational Physics-Informed Neural Networks With Domain Decomposition
• Bayesian Physics-Informed Neural Networks for real-world nonlinear dynamical systems
• On the numerical approximation of the Perron-Frobenius and Koopman operator
• Physics-Informed Neural Nets for Control of Dynamical Systems
• Dynamical Energy Analysis - determining wave energy distributions in complex vibro-acoustical structures
• Deep least-squares methods: an unsupervised learning-based numerical method for solving elliptic PDEs
• Variational Physics Informed Neural Networks: the role of quadratures and test functions
• An early warning indicator for atmospheric blocking events using transfer operators
• Unveiling the optimization process of Physics Informed Neural Networks: How accurate and competitive can PINNs be?
• A Neural Network Approach for High-Dimensional Optimal Control Applied to Multi-Agent Path Finding
• Crisis of the Chaotic Attractor of a Climate Model: A Transfer Operator Approach
• Solving PDEs by Variational Physics-Informed Neural Networks: an a posteriori error analysis
• Dynamical energy analysis for built-up acoustic systems at high frequencies
• Optimizing Variational Physics-Informed Neural Networks Using Least Squares
• Neural Control of Discrete Weak Formulations: Galerkin, Least-Squares and Minimal-Residual Methods with Quasi-Optimal Weights
• Transfer operator approach to ray-tracing in circular domains