{"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/a-more-globally-accurate-dimensionality","title":"A more globally accurate dimensionality reduction method using triplets","arxiv_id":"1803.00854","date":"2018-03-01","proceeding":null,"authors":["Ehsan Amid","Manfred K. Warmuth"],"abstract":"We first show that the commonly used dimensionality reduction (DR) methods\nsuch as t-SNE and LargeVis poorly capture the global structure of the data in\nthe low dimensional embedding. We show this via a number of tests for the DR\nmethods that can be easily applied by any practitioner to the dataset at hand.\nSurprisingly enough, t-SNE performs the best w.r.t. the commonly used measures\nthat reward the local neighborhood accuracy such as precision-recall while\nhaving the worst performance in our tests for global structure. We then\ncontrast the performance of these two DR method against our new method called\nTriMap. The main idea behind TriMap is to capture higher orders of structure\nwith triplet information (instead of pairwise information used by t-SNE and\nLargeVis), and to minimize a robust loss function for satisfying the chosen\ntriplets. We provide compelling experimental evidence on large natural datasets\nfor the clear advantage of the TriMap DR results. As LargeVis, TriMap scales\nlinearly with the number of data points.","url_abs":"http://arxiv.org/abs/1803.00854v1","url_pdf":"http://arxiv.org/pdf/1803.00854v1.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":"a-more-globally-accurate-dimensionality","repo_url":"https://github.com/eamid/trimap","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"dimensionality-reduction","task_name":"Dimensionality Reduction"},{"task_slug":null,"task_name":"Triplet"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.00854","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}