{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/heavy-tailed-kernels-reveal-a-finer-cluster","title":"Heavy-tailed kernels reveal a finer cluster structure in t-SNE visualisations","arxiv_id":"1902.05804","date":"2019-02-15","proceeding":null,"authors":["Dmitry Kobak","George Linderman","Stefan Steinerberger","Yuval Kluger","Philipp Berens"],"abstract":"T-distributed stochastic neighbour embedding (t-SNE) is a widely used data\nvisualisation technique. It differs from its predecessor SNE by the\nlow-dimensional similarity kernel: the Gaussian kernel was replaced by the\nheavy-tailed Cauchy kernel, solving the \"crowding problem\" of SNE. Here, we\ndevelop an efficient implementation of t-SNE for a $t$-distribution kernel with\nan arbitrary degree of freedom $\\nu$, with $\\nu\\to\\infty$ corresponding to SNE\nand $\\nu=1$ corresponding to the standard t-SNE. Using theoretical analysis and\ntoy examples, we show that $\\nu<1$ can further reduce the crowding problem and\nreveal finer cluster structure that is invisible in standard t-SNE. We further\ndemonstrate the striking effect of heavier-tailed kernels on large real-life\ndata sets such as MNIST, single-cell RNA-sequencing data, and the HathiTrust\nlibrary. We use domain knowledge to confirm that the revealed clusters are\nmeaningful. Overall, we argue that modifying the tail heaviness of the t-SNE\nkernel can yield additional insight into the cluster structure of the data.","url_abs":"http://arxiv.org/abs/1902.05804v2","url_pdf":"http://arxiv.org/pdf/1902.05804v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"heavy-tailed-kernels-reveal-a-finer-cluster","repo_url":"https://github.com/berenslab/finer-tsne","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"heavy-tailed-kernels-reveal-a-finer-cluster","repo_url":"https://github.com/dkobak/finer-tsne","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1902.05804","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}