Research map / Learning theory and algorithms / Matrix and tensor methods
Exploiting Data Geometry in Machine Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
A survey-style overview of methods for identifying and exploiting geometric structure in high-dimensional and non-Euclidean data for machine learning.
Problem
Identifying geometric structure in high-dimensional data, including non-Euclidean data such as graphs, strings, matrices, and data shaped by symmetries.
Approach
Discusses methods for discovering geometric structure in data and using it in learning algorithms, rather than assuming data lies in a flat high-dimensional vector space. Details beyond the abstract are not available.
Closest papers by meaning
- Data-Informed Geometric Space Selection (NeurIPS 2023 · similarity 0.86)
- Wrapped Gaussian on the manifold of Symmetric Positive Definite Matrices (ICML 2025 · similarity 0.86)
- Geometric Mean Metric Learning (ICML 2016 · similarity 0.85)
- Log-Euclidean Signatures for Intrinsic Distances Between Unaligned Datasets (ICML 2022 · similarity 0.85)
- Graph Geometry-Preserving Autoencoders (ICML 2024 · similarity 0.83)
- Geometry Awakening: Cross-Geometry Learning Exhibits Superiority over Individual Structures (NeurIPS 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.