Convergence analysis of Parametric Probabilistic Manifold Decomposition

DOI10.48550/arXiv.2608.29105MaRDI QIDQ7285174arXivFDO

Authors Jiaming Guo, D. Xiao, Dunhui Xiao

Publication date 29 August 2026

Published in arXiv

Tldr We present a coupled perturbation analysis for Parametric Probabilistic Manifold Decomposition (PPMD), the first to track error propagation through all learned components in this data-driven nonlinear ROM method, yielding deterministic and high-probability trajectory error bounds and consistency in probability.

Full work available at URL https://doi.org/10.48550/arXiv.2608.29105

arXiv classification

math.NA

Cites work

• A state space error estimate for POD-DEIM nonlinear model reduction
• A survey of projection-based model reduction methods for parametric dynamical systems
• A tailored convolutional neural network for nonlinear manifold learning of computational physics data using unstructured spatial discretizations
• An ensemble-proper orthogonal decomposition method for the nonstationary Navier-Stokes equations
• An online manifold learning approach for model reduction of dynamical systems
• Analyzing the discrepancy principle for kernelized spectral filter learning algorithms
• CALCULATION OF THE SMOOTHING SPLINE WITH WEIGHTED ROUGHNESS MEASURE
• Convergence of Numerical Approximations of the Incompressible Navier–Stokes Equations with Variable Density and Viscosity
• Diffusion maps
• Error bounds for derivative estimates based on spline smoothing of exact or noisy data
• Finite Element Approximation of the Nonstationary Navier–Stokes Problem III. Smoothing Property and Higher Order Error Estimates for Spatial Discretization
• Finite Element Approximation of the Nonstationary Navier–Stokes Problem. I. Regularity of Solutions and Second-Order Error Estimates for Spatial Discretization
• Finite-Element Approximation of the Nonstationary Navier–Stokes Problem. Part IV: Error Analysis for Second-Order Time Discretization
• Lipschitz regularity of graph Laplacians on random data clouds
• Manifold Approximations via Transported Subspaces: Model reduction for transport-dominated problems
• Mixed finite element formulation and error estimates based on proper orthogonal decomposition for the nonstationary Navier-Stokes equations
• Model reduction for transport-dominated problems via online adaptive bases and adaptive sampling
• Multivariate Smoothing Spline Functions
• Nonlinear model reduction by probabilistic manifold decomposition
• Numerical analysis of a projection-based stabilized POD-ROM for incompressible flows
• On Error Estimates of Projection Methods for Navier–Stokes Equations: First-Order Schemes
• On the improved rates of convergence for Matérn-type kernel ridge regression with application to calibration of computer models
• Optimal rates for the regularized least-squares algorithm
• Parametric Probabilistic Manifold Decomposition for Nonlinear Model Reduction
• POD-ROMs for Incompressible Flows Including Snapshots of the Temporal Derivative of the Full Order Solution
• Space-time least-squares Petrov-Galerkin projection for nonlinear model reduction
• Space-Time Reduced Basis Methods for Parametrized Unsteady Stokes Equations
• Spectral Convergence of Diffusion Maps: Improved Error Bounds and an Alternative Normalization
• Spectral convergence of graph Laplacian and heat kernel reconstruction in L^ from random samples
• The Rotation of Eigenvectors by a Perturbation. III
• Unconstrained and curvature-constrained shortest-path distances and their approximation
• VECTOR VALUED REPRODUCING KERNEL HILBERT SPACES OF INTEGRABLE FUNCTIONS AND MERCER THEOREM

This page was built for publication: Convergence analysis of Parametric Probabilistic Manifold Decomposition

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7285174)