{"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/robust-training-in-high-dimensions-via-block","title":"Robust Training in High Dimensions via Block Coordinate Geometric Median Descent","arxiv_id":"2106.08882","date":"2021-06-16","proceeding":null,"authors":["Anish Acharya","Abolfazl Hashemi","Prateek Jain","Sujay Sanghavi","Inderjit S. Dhillon","Ufuk Topcu"],"abstract":"Geometric median (\\textsc{Gm}) is a classical method in statistics for achieving a robust estimation of the uncorrupted data; under gross corruption, it achieves the optimal breakdown point of 0.5. However, its computational complexity makes it infeasible for robustifying stochastic gradient descent (SGD) for high-dimensional optimization problems. In this paper, we show that by applying \\textsc{Gm} to only a judiciously chosen block of coordinates at a time and using a memory mechanism, one can retain the breakdown point of 0.5 for smooth non-convex problems, with non-asymptotic convergence rates comparable to the SGD with \\textsc{Gm}.","url_abs":"https://arxiv.org/abs/2106.08882v1","url_pdf":"https://arxiv.org/pdf/2106.08882v1.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":"robust-training-in-high-dimensions-via-block","repo_url":"https://github.com/anishacharya/Optimization-Mavericks","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"robust-training-in-high-dimensions-via-block","repo_url":"https://github.com/anishacharya/BGMD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[{"method_slug":"sgd","method_name":"SGD"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-mnist","task":"Image Classification","dataset":"MNIST","model":"CNN-5 Layer","rank_in_archive_order":71,"of":81,"metrics":{"Accuracy":"99.27"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2106.08882","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08882"}},"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/anishacharya/BGMD","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/anishacharya/Optimization-Mavericks","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"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":"98daaabb6137b3ad","entry":"get_gar","repo":"anishacharya/Optimization-Mavericks","repo_kind":"official","path":"src/aggregation_manager/gar_helper.py","file_url":"https://github.com/anishacharya/Optimization-Mavericks/blob/HEAD/src/aggregation_manager/gar_helper.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98daaabb6137b3ad"}},{"code_sha256_prefix":"7e1a394c4f364f7f","entry":"get_trainer","repo":"anishacharya/Optimization-Mavericks","repo_kind":"official","path":"optimization_driver.py","file_url":"https://github.com/anishacharya/Optimization-Mavericks/blob/HEAD/optimization_driver.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7e1a394c4f364f7f"}},{"code_sha256_prefix":"47b9776f710aa15d","entry":"smooth","repo":"anishacharya/Optimization-Mavericks","repo_kind":"official","path":"plot_results.py","file_url":"https://github.com/anishacharya/Optimization-Mavericks/blob/HEAD/plot_results.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"47b9776f710aa15d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}