The Mathematical Foundations of Manifold Learning
Manifold learning is a popular and quickly-growing subfield of machine learning based on the assumption that one's observed data lie on a low-dimensional manifold embedded in a higher-dimensional space. This thesis presents a mathematical perspective on manifold learning, delving into the intersection of kernel learning, spectral graph theory, and differential geometry. Emphasis is placed on the remarkable interplay between graphs and manifolds, which forms the foundation for the widely-used technique of manifold regularization. This work is written to be accessible to a broad mathematical audience, including machine learning researchers and practitioners interested in understanding the theorems underlying popular manifold learning algorithms and dimensionality reduction techniques.
Code (0)
등록된 구현이 없습니다.
Tasks
BIG-bench Machine LearningDimensionality ReductionSimilar Papers 제목 키워드 기반
Manifold-based Shapley for SAR Recognization Network Explanation
Explainable artificial intelligence (XAI) holds immense significance in enhancing the deep neural network's transparency and credibility, particularly in some risky and high-cost scenarios, like synthetic aperture radar …
Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)SMaRt: Improving GANs with Score Matching Regularity
Generative adversarial networks (GANs) usually struggle in learning from highly diverse data, whose underlying manifold is complex. In this work, we revisit the mathematical foundations of GANs, and theoretically reveal …
validA PDE Perspective on Generative Diffusion Models
Score-based diffusion models have emerged as a powerful class of generative methods, achieving state-of-the-art performance across diverse domains. Despite their empirical success, the mathematical foundations of those m…
Learning from Frustration: Torsor CNNs on Graphs
Most equivariant neural networks rely on a single global symmetry, limiting their use in domains where symmetries are instead local. We introduce Torsor CNNs, a framework for learning on graphs with local symmetries enco…
Survey: Geometric Foundations of Data Reduction
This survey is written in summer, 2016. The purpose of this survey is to briefly introduce nonlinear dimensionality reduction (NLDR) in data reduction. The first two NLDR were respectively published in Science in 2000 in…
Dimensionality ReductionSurvey