{"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/outlier-robust-high-dimensional-sparse-1","title":"Outlier-Robust High-Dimensional Sparse Estimation via Iterative Filtering","arxiv_id":"1911.08085","date":"2019-11-19","proceeding":"NeurIPS 2019 12","authors":["Ilias Diakonikolas","Sushrut Karmalkar","Daniel Kane","Eric Price","Alistair Stewart"],"abstract":"We study high-dimensional sparse estimation tasks in a robust setting where a constant fraction of the dataset is adversarially corrupted. Specifically, we focus on the fundamental problems of robust sparse mean estimation and robust sparse PCA. We give the first practically viable robust estimators for these problems. In more detail, our algorithms are sample and computationally efficient and achieve near-optimal robustness guarantees. In contrast to prior provable algorithms which relied on the ellipsoid method, our algorithms use spectral techniques to iteratively remove outliers from the dataset. Our experimental evaluation on synthetic data shows that our algorithms are scalable and significantly outperform a range of previous approaches, nearly matching the best error rate without corruptions.","url_abs":"https://arxiv.org/abs/1911.08085v1","url_pdf":"https://arxiv.org/pdf/1911.08085v1.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":"outlier-robust-high-dimensional-sparse-1","repo_url":"https://github.com/sushrutk/robust_sparse_mean_estimation","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"outlier-robust-high-dimensional-sparse-1","repo_url":"https://github.com/guptashvm/sparse-gd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"outlier-robust-high-dimensional-sparse-1","repo_url":"https://github.com/huihui0902/robust_mean_estimation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[{"method_slug":"pca","method_name":"PCA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1911.08085","atlas_url":"https://app.syntology.ai/?focus=1911.08085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08085"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/huihui0902/robust_mean_estimation","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sushrutk/robust_sparse_mean_estimation","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/guptashvm/sparse-gd","reach":{"status":"ok"}}],"summary":{"ran":3,"ran_violates":1,"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1},"listed":{"samples":3,"ran":3,"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":"cf656e059d09ed94","entry":"acc","repo":"huihui0902/robust_mean_estimation","repo_kind":"listed","path":"robust_mean_estimate_acc.py","file_url":"https://github.com/huihui0902/robust_mean_estimation/blob/HEAD/robust_mean_estimate_acc.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cf656e059d09ed94"}},{"code_sha256_prefix":"88cf0fae09eb4f9c","entry":"err","repo":"sushrutk/robust_sparse_mean_estimation","repo_kind":"official","path":"robustlib.py","file_url":"https://github.com/sushrutk/robust_sparse_mean_estimation/blob/HEAD/robustlib.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"88cf0fae09eb4f9c"}},{"code_sha256_prefix":"7f4024450c5b5604","entry":"err","repo":"huihui0902/robust_mean_estimation","repo_kind":"listed","path":"robustlib.py","file_url":"https://github.com/huihui0902/robust_mean_estimation/blob/HEAD/robustlib.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7f4024450c5b5604"}},{"code_sha256_prefix":"292414dc4e6ce863","entry":"err_rspca","repo":"sushrutk/robust_sparse_mean_estimation","repo_kind":"official","path":"robustlib.py","file_url":"https://github.com/sushrutk/robust_sparse_mean_estimation/blob/HEAD/robustlib.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"292414dc4e6ce863"}},{"code_sha256_prefix":"88e19c4ec091c85b","entry":"get_error","repo":"sushrutk/robust_sparse_mean_estimation","repo_kind":"official","path":"robustlib.py","file_url":"https://github.com/sushrutk/robust_sparse_mean_estimation/blob/HEAD/robustlib.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"88e19c4ec091c85b"}},{"code_sha256_prefix":"3e161617d69a519f","entry":"pre_processing","repo":"huihui0902/robust_mean_estimation","repo_kind":"listed","path":"robust_mean_estimate_acc.py","file_url":"https://github.com/huihui0902/robust_mean_estimation/blob/HEAD/robust_mean_estimate_acc.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3e161617d69a519f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}