Convergence of Hessian estimator from random samples on a manifold

03/22/2023
by   Chih-Wei Chen, et al.
0

We provide a systematic convergence analysis of the Hessian operator estimator from random samples supported on a low dimensional manifold. We show that the impact of the nonuniform sampling and the curvature on the widely applied Hessian operator estimator is asymptotically negligible.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/16/2020

GO Hessian for Expectation-Based Objectives

An unbiased low-variance gradient estimator, termed GO gradient, was pro...
research
02/10/2023

Hessian Based Smoothing Splines for Manifold Learning

We propose a multidimensional smoothing spline algorithm in the context ...
research
04/18/2023

Hessian and increasing-Hessian orderings of multivariate skew-elliptical random vectors

In this work, we establish some stochastic comparison results for multiv...
research
01/26/2022

Towards Sharp Stochastic Zeroth Order Hessian Estimators over Riemannian Manifolds

We study Hessian estimators for real-valued functions defined over an n-...
research
12/16/2021

A new locally linear embedding scheme in light of Hessian eigenmap

We provide a new interpretation of Hessian locally linear embedding (HLL...
research
08/28/2022

Visualizing high-dimensional loss landscapes with Hessian directions

Analyzing geometric properties of high-dimensional loss functions, such ...
research
01/23/2019

High-dimensional Interactions Detection with Sparse Principal Hessian Matrix

In statistical methods, interactions are the contributions from the prod...

Please sign up or login with your details

Forgot password? Click here to reset