Abstract | ||
---|---|---|
The paper presents an O(N log N)-implementation of t-SNE -- an embedding technique that is commonly used for the visualization of high-dimensional data in scatter plots and that normally runs in O(N^2). The new implementation uses vantage-point trees to compute sparse pairwise similarities between the input data objects, and it uses a variant of the Barnes-Hut algorithm - an algorithm used by astronomers to perform N-body simulations - to approximate the forces between the corresponding points in the embedding. Our experiments show that the new algorithm, called Barnes-Hut-SNE, leads to substantial computational advantages over standard t-SNE, and that it makes it possible to learn embeddings of data sets with millions of objects. |
Year | Venue | Field |
---|---|---|
2013 | CoRR | Data set,Computer science,Theoretical computer science,Artificial intelligence,Time complexity,Pairwise comparison,Embedding,Visualization,Algorithm,Barnes–Hut simulation,Data objects,Scatter plot,Machine learning |
DocType | Volume | Citations |
Journal | abs/1301.3342 | 14 |
PageRank | References | Authors |
2.72 | 0 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
van der maaten | 1 | 763 | 48.75 |
laurens | 2 | 14 | 2.72 |