{"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/sketchboost-fast-gradient-boosted-decision","title":"SketchBoost: Fast Gradient Boosted Decision Tree for Multioutput Problems","arxiv_id":"2211.12858","date":"2022-11-23","proceeding":null,"authors":["Leonid Iosipoi","Anton Vakhrushev"],"abstract":"Gradient Boosted Decision Tree (GBDT) is a widely-used machine learning algorithm that has been shown to achieve state-of-the-art results on many standard data science problems. We are interested in its application to multioutput problems when the output is highly multidimensional. Although there are highly effective GBDT implementations, their scalability to such problems is still unsatisfactory. In this paper, we propose novel methods aiming to accelerate the training process of GBDT in the multioutput scenario. The idea behind these methods lies in the approximate computation of a scoring function used to find the best split of decision trees. These methods are implemented in SketchBoost, which itself is integrated into our easily customizable Python-based GPU implementation of GBDT called Py-Boost. Our numerical study demonstrates that SketchBoost speeds up the training process of GBDT by up to over 40 times while achieving comparable or even better performance.","url_abs":"https://arxiv.org/abs/2211.12858v1","url_pdf":"https://arxiv.org/pdf/2211.12858v1.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":"sketchboost-fast-gradient-boosted-decision","repo_url":"https://github.com/sb-ai-lab/sketchboost-paper","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.12858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.12858"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sb-ai-lab/sketchboost-paper","reach":null}],"summary":{"ran":1,"ran_fixture":1,"unverified":4},"by_repo_kind":{"official":{"samples":6,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"eb863ac938ac265e","entry":"BoostUtils","repo":"sb-ai-lab/sketchboost-paper","repo_kind":"official","path":"GBDTMO/gbdtmo/gbdtmo.py","file_url":"https://github.com/sb-ai-lab/sketchboost-paper/blob/HEAD/GBDTMO/gbdtmo/gbdtmo.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"eb863ac938ac265e"}},{"code_sha256_prefix":"8ee82463b6ec6dec","entry":"map_bin_column","repo":"sb-ai-lab/sketchboost-paper","repo_kind":"official","path":"GBDTMO/gbdtmo/gbdtmo.py","file_url":"https://github.com/sb-ai-lab/sketchboost-paper/blob/HEAD/GBDTMO/gbdtmo/gbdtmo.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8ee82463b6ec6dec"}},{"code_sha256_prefix":"73928a49bc1bb766","entry":"GBDTMulti","repo":"sb-ai-lab/sketchboost-paper","repo_kind":"official","path":"GBDTMO/gbdtmo/gbdtmo.py","file_url":"https://github.com/sb-ai-lab/sketchboost-paper/blob/HEAD/GBDTMO/gbdtmo/gbdtmo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"73928a49bc1bb766"}},{"code_sha256_prefix":"768ffb849b4f0e61","entry":"_get_bins_maps","repo":"sb-ai-lab/sketchboost-paper","repo_kind":"official","path":"GBDTMO/gbdtmo/gbdtmo.py","file_url":"https://github.com/sb-ai-lab/sketchboost-paper/blob/HEAD/GBDTMO/gbdtmo/gbdtmo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"768ffb849b4f0e61"}},{"code_sha256_prefix":"80674b3cff115bd7","entry":"construct_bin_column","repo":"sb-ai-lab/sketchboost-paper","repo_kind":"official","path":"GBDTMO/gbdtmo/gbdtmo.py","file_url":"https://github.com/sb-ai-lab/sketchboost-paper/blob/HEAD/GBDTMO/gbdtmo/gbdtmo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"80674b3cff115bd7"}},{"code_sha256_prefix":"f2429ec0fdaef4a4","entry":"get_bins_maps","repo":"sb-ai-lab/sketchboost-paper","repo_kind":"official","path":"GBDTMO/gbdtmo/gbdtmo.py","file_url":"https://github.com/sb-ai-lab/sketchboost-paper/blob/HEAD/GBDTMO/gbdtmo/gbdtmo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f2429ec0fdaef4a4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}