betaFeedback

WorksMathematics

Variance Stable Gaussian Smoothing Estimator for Arbitrary High-order Derivatives

Abstract

Computing high-order partial derivatives in high dimensions by automatic differentiation can be costly in both computation and memory. Stein's identity offers an alternative through Gaussian smoothing, but the variance of the resulting estimators can diverge as the step size tends to zero, even with antithetic sampling. We propose a variance stabilization technique that extends antithetic sampling from a reflection pair to nn equally spaced points on a circle in the complex plane. Under local analyticity, we prove that, when nn is at least the derivative order, the bias is of order O(σn)O(σ^n) and the variance remains bounded as the smoothing step size σσ tends to zero. Numerical experiments support these predictions and demonstrate the effectiveness of the estimator in physics-informed neural networks (PINNs) for polyharmonic and Cahn–Hilliard equations. The technique mitigates the bias-variance trade-off in smoothing-based derivative estimation and is useful for PINNs solving high-order partial differential equations.

Paper details

vlnc:W_zhgsyf3x
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
arXiv nonexclusive license
Usage

views · 0

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Mathematics

Not recorded for this paper

View statement
Looking for related papers…