UMAP: Uniform Manifold Approximation and Projection for Dimension
Reduction
L. McInnes, J. Healy, and J. Melville. (2018)cite arxiv:1802.03426Comment: Reference implementation available at http://github.com/lmcinnes/umap.
Abstract
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 has no computational restrictions on embedding
dimension, making it viable as a general purpose dimension reduction technique
for machine learning.
Description
[1802.03426] UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
%0 Generic
%1 mcinnes2018uniform
%A McInnes, Leland
%A Healy, John
%A Melville, James
%D 2018
%K dimensionality-reduction visualization
%T UMAP: Uniform Manifold Approximation and Projection for Dimension
Reduction
%U http://arxiv.org/abs/1802.03426
%X 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 has no computational restrictions on embedding
dimension, making it viable as a general purpose dimension reduction technique
for machine learning.
@misc{mcinnes2018uniform,
abstract = {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 has no computational restrictions on embedding
dimension, making it viable as a general purpose dimension reduction technique
for machine learning.},
added-at = {2020-07-21T15:43:06.000+0200},
author = {McInnes, Leland and Healy, John and Melville, James},
biburl = {https://www.bibsonomy.org/bibtex/24e07b95c8d7f645650f2c678743df036/bsc},
description = {[1802.03426] UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction},
interhash = {39e87180fe340432856512bc17149e62},
intrahash = {4e07b95c8d7f645650f2c678743df036},
keywords = {dimensionality-reduction visualization},
note = {cite arxiv:1802.03426Comment: Reference implementation available at http://github.com/lmcinnes/umap},
timestamp = {2020-07-21T15:43:06.000+0200},
title = {UMAP: Uniform Manifold Approximation and Projection for Dimension
Reduction},
url = {http://arxiv.org/abs/1802.03426},
year = 2018
}