{"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/fast-k-nearest-neighbour-search-via","title":"Fast k-Nearest Neighbour Search via Prioritized DCI","arxiv_id":"1703.00440","date":"2017-03-01","proceeding":"ICML 2017 8","authors":["Ke Li","Jitendra Malik"],"abstract":"Most exact methods for k-nearest neighbour search suffer from the curse of\ndimensionality; that is, their query times exhibit exponential dependence on\neither the ambient or the intrinsic dimensionality. Dynamic Continuous Indexing\n(DCI) offers a promising way of circumventing the curse and successfully\nreduces the dependence of query time on intrinsic dimensionality from\nexponential to sublinear. In this paper, we propose a variant of DCI, which we\ncall Prioritized DCI, and show a remarkable improvement in the dependence of\nquery time on intrinsic dimensionality. In particular, a linear increase in\nintrinsic dimensionality, or equivalently, an exponential increase in the\nnumber of points near a query, can be mostly counteracted with just a linear\nincrease in space. We also demonstrate empirically that Prioritized DCI\nsignificantly outperforms prior methods. In particular, relative to\nLocality-Sensitive Hashing (LSH), Prioritized DCI reduces the number of\ndistance evaluations by a factor of 14 to 116 and the memory consumption by a\nfactor of 21.","url_abs":"http://arxiv.org/abs/1703.00440v2","url_pdf":"http://arxiv.org/pdf/1703.00440v2.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":"fast-k-nearest-neighbour-search-via","repo_url":"https://github.com/aminfadaei116/Fast-KNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"fast-k-nearest-neighbour-search-via","repo_url":"https://github.com/dnbaker/frp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}