跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.19653 · v1

A Geometric Understanding of Denoising Autoencoder with Applications to Image Denoising

首次提交 2026-11-15 06:49
版本更新 2026-11-15 06:49
雷达观测 2026-11-17 12:06
arXiv ↗PDF ↗

摘要

Denoising autoencoders have shown strong empirical performance in recovering clean data from their noisy observations, yet their underlying statistical behavior remains underexplored. In this paper, we study denoising autoencoders under the manifold hypothesis, assuming that clean data are supported on low-dimensional smooth manifolds embedded in a high-dimensional ambient space, while noisy observations are generated by isotropic Gaussian noise. We establish generalization guarantees in three geometric scenarios: a single manifold, a pairwise separated finite union of manifolds, and a finite union of intersecting manifolds. Using local chart representations, partitions of unity, and neural network approximation, we derive upper bounds for the expected squared reconstruction error for denoising autoencoder. In the single-manifold and separated-union scenarios, the error consists of a sample-dependent statistical term of order n−2/(d+2)log⁡4nn^{-2/(d+2)}\log^4 n, a residual term of order dσ2/Ddσ^2/D caused by tangential noise, and an exponentially small tail term associated with failure of the manifold projection. Here DD is the data ambient dimension, dd is the intrinsic dimension of the clean-data manifold, and σ2σ^2 is the expected squared noise magnitude. In the scenario of intersecting manifolds, we further identify an additional ambiguity term determined by the probability mass near the intersection neighborhood. Numerical experiments on synthetic manifolds and real image datasets support the predicted sample-size scaling law and illustrate the additional reconstruction ambiguity near manifold intersections.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-15 06:49 · 最新观测版本

A Geometric Understanding of Denoising Autoencoder with Applications to Image Denoising

Denoising autoencoders have shown strong empirical performance in recovering clean data from their noisy observations, yet their underlying statistical behavior remains underexplored. In this paper, we study denoising autoencoders under the manifold hypothesis, assuming that clean data are supported on low-dimensional smooth manifolds embedded in a high-dimensional ambient space, while noisy observations are generated by isotropic Gaussian noise. We establish generalization guarantees in three geometric scenarios: a single manifold, a pairwise separated finite union of manifolds, and a finite union of intersecting manifolds. Using local chart representations, partitions of unity, and neural network approximation, we derive upper bounds for the expected squared reconstruction error for denoising autoencoder. In the single-manifold and separated-union scenarios, the error consists of a sample-dependent statistical term of order n−2/(d+2)log⁡4nn^{-2/(d+2)}\log^4 n, a residual term of order dσ2/Ddσ^2/D caused by tangential noise, and an exponentially small tail term associated with failure of the manifold projection. Here DD is the data ambient dimension, dd is the intrinsic dimension of the clean-data manifold, and σ2σ^2 is the expected squared noise magnitude. In the scenario of intersecting manifolds, we further identify an additional ambiguity term determined by the probability mass near the intersection neighborhood. Numerical experiments on synthetic manifolds and real image datasets support the predicted sample-size scaling law and illustrate the additional reconstruction ambiguity near manifold intersections.

查看此版本解读 →查看此版本原文 ↗