Corpus ID: 3641284

UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction

  title={UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction},
  author={L. McInnes and J. Healy},
  • L. McInnes, J. Healy
  • Published 2018
  • Mathematics, Computer Science
  • ArXiv
  • UMAP (Uniform Manifold Approximation and Projection) is a novel manifold learning technique for dimension reduction. UMAP is constructed from a theoretical framework based in Riemannian geometry and algebraic topology. The result is a practical scalable algorithm that applies to real world data. The UMAP algorithm is competitive with t-SNE for visualization quality, and arguably preserves more of the global structure with superior run time performance. Furthermore, UMAP as described has no… CONTINUE READING
    1,408 Citations
    UMAP: Uniform Manifold Approximation and Projection
    • 731
    • PDF
    Manifold Learning via Manifold Deflation
    The mathematics of UMAP
    Extendable and invertible manifold learning with geometry regularized autoencoders
    No Pressure! Addressing the Problem of Local Minima in Manifold Learning Algorithms
    Deep Manifold Computing and Visualization
    Markov-Lipschitz Deep Learning
    • 4
    • PDF


    Mapping a Manifold of Perceptual Observations
    • 293
    • PDF
    Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
    • 6,393
    • PDF
    Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering
    • 3,782
    • PDF
    A global geometric framework for nonlinear dimensionality reduction.
    • 9,998
    • Highly Influential
    • PDF
    Information Retrieval Perspective to Nonlinear Dimensionality Reduction for Data Visualization
    • 305
    • PDF
    Distance Metric Learning: A Comprehensive Survey
    • 528
    • PDF
    Gaussian mixture models with Wasserstein distance
    • 7
    • PDF