跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.20275 · v1

The Manifold-Index Model: provably and efficiently avoiding the statistical and computational curse of dimensionality

首次提交 2026-11-16 06:08
版本更新 2026-11-16 06:08
雷达观测 2026-11-17 17:12
arXiv ↗PDF ↗

摘要

We study vector-valued regression with predictors filling a tube around an unknown mm-dimensional manifold M\mathcal{M} in RD\mathbb{R}^D. In the Manifold-Index Model, the mean response is F=f∘ΠMF=f\circΠ_{\mathcal{M}}, where ΠMΠ_{\mathcal{M}} is the nearest-point projection onto M\mathcal{M} and f:M→Rpf:\mathcal{M}\to\mathbb{R}^p is a possibly non-injective link function. Multiscale ANisotropic lOcal Regression (MANOR) estimates tangent planes by multiscale PCA of predictors with similar responses, then refines them by pooling outer products of local slopes. The neighborhoods narrow tangentially while retaining complete normal fibers. We assume a Lipschitz link differential and bounded response noise. For p≥mp\ge m, under our geometric and sampling conditions, nn independent observations give mean tangent-space error of order n−2/(m+4)n^{-2/(m+4)} and integrated squared prediction error at the mm-dimensional nonparametric rate n−4/(m+4)n^{-4/(m+4)}, up to logarithmic factors. In a scaling regime with fixed intrinsic dimension, model and scale parameters, and ratio of manifold volume to the mm-th power of its reach, the required sample size grows polynomially in D+pD+p, and computation is polynomial in nn, DD and pp. Numerical experiments on curves with non-monotone links and surfaces with vector-valued responses compare observed convergence rates with the theoretical bounds; a Langevin dynamics example tests prediction of hitting probabilities under an approximate manifold-index model.

作者备注:89 pages, 17 figures, 8 tables

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 · 2026-11-16 06:08 · 最新观测版本

The Manifold-Index Model: provably and efficiently avoiding the statistical and computational curse of dimensionality

We study vector-valued regression with predictors filling a tube around an unknown mm-dimensional manifold M\mathcal{M} in RD\mathbb{R}^D. In the Manifold-Index Model, the mean response is F=f∘ΠMF=f\circΠ_{\mathcal{M}}, where ΠMΠ_{\mathcal{M}} is the nearest-point projection onto M\mathcal{M} and f:M→Rpf:\mathcal{M}\to\mathbb{R}^p is a possibly non-injective link function. Multiscale ANisotropic lOcal Regression (MANOR) estimates tangent planes by multiscale PCA of predictors with similar responses, then refines them by pooling outer products of local slopes. The neighborhoods narrow tangentially while retaining complete normal fibers. We assume a Lipschitz link differential and bounded response noise. For p≥mp\ge m, under our geometric and sampling conditions, nn independent observations give mean tangent-space error of order n−2/(m+4)n^{-2/(m+4)} and integrated squared prediction error at the mm-dimensional nonparametric rate n−4/(m+4)n^{-4/(m+4)}, up to logarithmic factors. In a scaling regime with fixed intrinsic dimension, model and scale parameters, and ratio of manifold volume to the mm-th power of its reach, the required sample size grows polynomially in D+pD+p, and computation is polynomial in nn, DD and pp. Numerical experiments on curves with non-monotone links and surfaces with vector-valued responses compare observed convergence rates with the theoretical bounds; a Langevin dynamics example tests prediction of hitting probabilities under an approximate manifold-index model.

查看此版本解读 →查看此版本原文 ↗