Residual Stopping and Pointwise Inference for Nonuniform Entropic Self-Transport
Loading original first page…
Abstract
We study observable residual stopping for the half-self-Sinkhorn iteration with iid samples from a fixed positive smooth density on the one- or two-dimensional torus. For the normalized periodic Gaussian, assume that ε→0, nε^(3d/2)→∞, and nε^(d/2+3)→0. Starting from the constant scaling, we stop at the first projective square-root-mass residual below t_n=n^(-1/2)ε^(-γ), where 0<γ<d/4 is fixed. The stopped score has the same pointwise Gaussian limit, centered at the true density score, as the exactly scaled empirical estimator. Its attained residual lies between ct_n and t_n with probability tending to one for every fixed 0<c<1/2, although √(n) t_n→∞. The stopping index is asymptotic to (d/4-γ)log(1/ε)/log2 in probability. For the coefficient-one threshold, uniform sampling already gives a different score limit when γ≥ d/4. The proof retains the iteration-dependent empirical-norm error and uses a normalized-row cancellation to control nonuniform initialization in dimension two.
Read the full paper in the original PDF.
Edition files
- Residual_Stopping_and_Pointwise_Inference.pdf140.9 KiB · pdf
SHA-256
657248b81ffe8fc2f218feb182a8a2b2837d263c1030d2850c78cb9770dec7a9 - Revised_publication_package.zip164.2 KiB · package
SHA-256
d0d3a58652adc6b8197988551a1097fc8601e135463a05b8081618f53b64e11c
Available editions
Research details
- Subjects
- Mathematics · Probability and Statistics
- Keywords
- entropic self-transport, Sinkhorn iteration, statistical stopping, score estimation, pointwise inference
- Manuscript date
- 2026-10-18
- Reader reuse
- No additional permission granted
Scope
Observable first-residual stopping preserves the pointwise Gaussian score limit on one- and two-dimensional tori under the explicit bandwidth and tolerance conditions, with a sharp stopping-count law and tolerance obstruction.
Reproduction
The paper has 13 pages. The editable-source archive contains 12 files. Compile the included TeX assembly using code/build_pdf.py or a compatible engine. code/verify_package.py checks public file identities.