Asymptotic Theory of ℓ_1-Regularized PDE Identification from a Single Noisy Trajectory

by   Yuchen He, et al.

We prove the support recovery for a general class of linear and nonlinear evolutionary partial differential equation (PDE) identification from a single noisy trajectory using ℓ_1 regularized Pseudo-Least Squares model (ℓ_1-PsLS). In any associative ℝ-algebra generated by finitely many differentiation operators that contain the unknown PDE operator, applying ℓ_1-PsLS to a given data set yields a family of candidate models with coefficients 𝐜(λ) parameterized by the regularization weight λ≥ 0. The trace of {𝐜(λ)}_λ≥ 0 suffers from high variance due to data noises and finite difference approximation errors. We provide a set of sufficient conditions which guarantee that, from a single trajectory data denoised by a Local-Polynomial filter, the support of 𝐜(λ) asymptotically converges to the true signed-support associated with the underlying PDE for sufficiently many data and a certain range of λ. We also show various numerical experiments to validate our theory.



There are no comments yet.


page 1

page 2

page 3

page 4


Robust PDE Identification from Noisy Data

We propose robust methods to identify underlying Partial Differential Eq...

Identification of Underlying Dynamic System from Noisy Data with Splines

In this paper, we propose a two-stage method called Spline Assisted Part...

Error bounds for PDE-regularized learning

In this work we consider the regularization of a supervised learning pro...

Methods to Recover Unknown Processes in Partial Differential Equations Using Data

We study the problem of identifying unknown processes embedded in time-d...

Convergence of the Two Point Flux Approximation and a novel fitted Two-Point Flux Approximation method for pricing options

In this paper, we deal with numerical approximations for solving the Bla...

PDE-Net: Learning PDEs from Data

In this paper, we present an initial attempt to learn evolution PDEs fro...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.