{"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/efficient-autotuning-of-hyperparameters-in","title":"Efficient Autotuning of Hyperparameters in Approximate Nearest Neighbor Search","arxiv_id":"1812.07484","date":"2018-12-18","proceeding":null,"authors":["Elias Jääsaari","Ville Hyvönen","Teemu Roos"],"abstract":"Approximate nearest neighbor algorithms are used to speed up nearest neighbor\nsearch in a wide array of applications. However, current indexing methods\nfeature several hyperparameters that need to be tuned to reach an acceptable\naccuracy--speed trade-off. A grid search in the parameter space is often\nimpractically slow due to a time-consuming index-building procedure. Therefore,\nwe propose an algorithm for automatically tuning the hyperparameters of\nindexing methods based on randomized space-partitioning trees. In particular,\nwe present results using randomized k-d trees, random projection trees and\nrandomized PCA trees. The tuning algorithm adds minimal overhead to the\nindex-building process but is able to find the optimal hyperparameters\naccurately. We demonstrate that the algorithm is significantly faster than\nexisting approaches, and that the indexing methods used are competitive with\nthe state-of-the-art methods in query time while being faster to build.","url_abs":"http://arxiv.org/abs/1812.07484v1","url_pdf":"http://arxiv.org/pdf/1812.07484v1.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":"efficient-autotuning-of-hyperparameters-in","repo_url":"https://github.com/vioshyvo/mrpt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"efficient-autotuning-of-hyperparameters-in","repo_url":"https://github.com/teemupitkanen/mrpt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"pca","method_name":"PCA"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.07484","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}