paper-with-me

Papers

Dimensionality reduction and width of deep neural networks based on topological degree theory

2025-11-10 · Xiao-Song Yang arxiv

In this paper we present a mathematical framework on linking of embeddings of compact topological spaces into Euclidean spaces and separability of linked embeddings under a specific class of dimension reduction maps. As applications of the established theory, we provide some fascinating insights into classification and approximation problems in deep learning theory in the setting of deep neural networks.

📄 PDF Abstract BibTeX arXiv:2511.06821

Code (0)

등록된 구현이 없습니다.

Tasks

Dimensionality Reduction

Similar Papers 제목 키워드 기반

Machine learning meets network science: dimensionality reduction for fast and efficient embedding of networks in the hyperbolic space

2016-02-21 · Josephine Maria Thomas, Alessandro Muscoloni, Sara Ciucci, Ginestra Bianconi 외

Complex network topologies and hyperbolic geometry seem specularly connected, and one of the most fascinating and challenging problems of recent complex network theory is to map a given network to its hyperbolic space. T…

Community DetectionDimensionality ReductionLink Prediction

FibeRed: Fiberwise Dimensionality Reduction of Topologically Complex Data with Vector Bundles

2022-06-13 · Luis Scoccola, Jose A. Perea

Datasets with non-trivial large scale topology can be hard to embed in low-dimensional Euclidean space with existing dimensionality reduction algorithms. We propose to model topologically complex datasets using vector bu…

Dimensionality Reduction

Topology-Preserving Dimensionality Reduction via Interleaving Optimization

2022-01-31 · Bradley J. Nelson, Yuan Luo

Dimensionality reduction techniques are powerful tools for data preprocessing and visualization which typically come with few guarantees concerning the topological correctness of an embedding. The interleaving distance b…

Data VisualizationDimensionality Reduction

Latent Manifold Reconstruction and Representation with Topological and Geometrical Regularization

2025-05-07 · Ren Wang, Pengcheng Zhou

Manifold learning aims to discover and represent low-dimensional structures underlying high-dimensional data while preserving critical topological and geometric properties. Existing methods often fail to capture local de…

Dimensionality Reduction

Depth separation for reduced deep networks in nonlinear model reduction: Distilling shock waves in nonlinear hyperbolic problems

2020-07-28 · Donsub Rim, Luca Venturi, Joan Bruna, Benjamin Peherstorfer

Classical reduced models are low-rank approximations using a fixed basis designed to achieve dimensionality reduction of large-scale systems. In this work, we introduce reduced deep networks, a generalization of classica…

Dimensionality Reduction