betaFeedback

WorksMathematics

Beyond Curvature Bias: Higher-Order Manifold Fitting via Multiscale Cancellation

Abstract

Local manifold-fitting procedures smooth noisy observations over neighborhoods of scale hh, inducing a systematic normal bias of order h2+σ2h^2+σ^2 that persists at the population level. We develop geometric bias cancellation (GBC), a multiscale framework for higher-order manifold recovery under ambient Gaussian noise. For procedures admitting a normal-bias expansion c(h,σ)b(x)+O(h4)c(h,σ)b(x)+O(h^4), we construct cross-scale correspondence using estimated normal fibers and show that second-order normal accuracy suffices for fourth-order correspondence accuracy. Canceling the leading geometric bias yields O(h4)O(h^4) population Hausdorff accuracy while preserving an embedded manifold diffeomorphic to the underlying manifold. We establish the required expansions and finite-sample recovery guarantees for successive tangent-space projection and Gaussian density ridges. For STSP, geometric bias cancellation also achieves an asymptotically vanishing Hausdorff error ratio relative to oracle bandwidth-tuned single-scale fitting. For the local contraction estimator of \citet{yao2023manifold}, we identify an obstruction to scalar bias cancellation and develop a directional cancellation achieving O(σ4)O(σ^4) population Hausdorff accuracy with uniform positive reach, as well as fourth-order finite-sample accuracy when n≳σ−(d+6)log⁡(1/σ)n\gtrsimσ^{-(d+6)}\log(1/σ). Simulations confirm the predicted improvement from second- to fourth-order population bias.

Paper details

vlnc:W_kdh56au8
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
CC-BY-NC-ND-4.0
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…