paper-with-me

홈 › Papers

A Geometric Analysis of PCA

2025-10-23 · Ayoub El Hanchi, Murat Erdogdu, Chris Maddison arxiv

What property of the data distribution determines the excess risk of principal component analysis? In this paper, we provide a precise answer to this question. We establish a central limit theorem for the error of the principal subspace estimated by PCA, and derive the asymptotic distribution of its excess risk under the reconstruction loss. We obtain a non-asymptotic upper bound on the excess risk of PCA that recovers, in the large sample limit, our asymptotic characterization. Underlying our contributions is the following result: we prove that the negative block Rayleigh quotient, defined on the Grassmannian, is generalized self-concordant along geodesics emanating from its minimizer of maximum rotation less than $π/4$.

📄 PDF Abstract BibTeX arXiv:2510.20978

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Geometry of Data

2022-03-14 · Parvaneh Joharinad, Jürgen Jost

Topological data analysis asks when balls in a metric space $(X,d)$ intersect. Geometric data analysis asks how much balls have to be enlarged to intersect. We connect this principle to the traditional core geometric con…

Topological Data Analysis

Geometric Structures and Patterns of Meaning: A PHATE Manifold Analysis of Chinese Character Embeddings

2025-09-23 · Wen G. Gong arxiv

We systematically investigate geometric patterns in Chinese character embeddings using PHATE manifold analysis. Through cross-validation across seven embedding models and eight dimensionality reduction methods, we observ…

Dimensionality Reduction

Computing the optimal keyboard through a geometric analysis of the English language

2023-10-17 · Jules Deschamps, Quentin Hubert, Lucas Ryckelynck

In the context of a group project for the course COMSW4995 002 - Geometric Data Analysis, we bring our attention to the design of fast-typing keyboards. Leveraging some geometric tools in an optimization framework allowe…

Understanding the Impact of Geometric Foundation Models on Vision-Language-Action Models

2026-05-23 · Yurou Yang, Muyuan Lin, Roberto Martin-Martin, Martin Labrie 외 arxiv

Recent work explores new opportunities at the intersection of vision-language-action models (VLAs) and geometric foundation models (GFMs) for 3D reconstruction, such as VGGT. While the resulting geometric VLAs often show…

3D Reconstruction

Improving Semantic Analysis on Point Clouds via Auxiliary Supervision of Local Geometric Priors

2020-01-14 · Lulu Tang, Ke Chen, Chaozheng Wu, Yu Hong 외

Existing deep learning algorithms for point cloud analysis mainly concern discovering semantic patterns from global configuration of local geometries in a supervised learning manner. However, very few explore geometric p…