{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:U3WSXIZRJVPRVZ7BWMLEVP2MVJ","short_pith_number":"pith:U3WSXIZR","schema_version":"1.0","canonical_sha256":"a6ed2ba3314d5f1ae7e1b3164abf4caa4c74066ae6b88bcfa21998f62f7e411d","source":{"kind":"arxiv","id":"2204.12399","version":2},"attestation_state":"computed","paper":{"title":"Streaming Algorithms for High-Dimensional Robust Statistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.DS","authors_text":"Ankit Pensia, Daniel M. Kane, Ilias Diakonikolas, Thanasis Pittas","submitted_at":"2022-04-26T15:57:07Z","abstract_excerpt":"We study high-dimensional robust statistics tasks in the streaming model. A recent line of work obtained computationally efficient algorithms for a range of high-dimensional robust estimation tasks. Unfortunately, all previous algorithms require storing the entire dataset, incurring memory at least quadratic in the dimension. In this work, we develop the first efficient streaming algorithms for high-dimensional robust statistics with near-optimal memory requirements (up to logarithmic factors). Our main result is for the task of high-dimensional robust mean estimation in (a strengthening of) H"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2204.12399","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2022-04-26T15:57:07Z","cross_cats_sorted":["cs.LG","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"b09c69f0ae66c42da773900390742845a0122196d486c875e3d52314a19077d1","abstract_canon_sha256":"d82f7a336e8d57e7264e429512aad02d397d329fde0bf63191c74c9bf6e54534"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:06:39.578260Z","signature_b64":"qosiSJksuS2QesqFZS2Rbl8Eq5eWel2yq40EMEkgO+Qk0Vf+Q/UbrcjBq4I2fZF3S5L8Ub+Oi567dKO9kgaLDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6ed2ba3314d5f1ae7e1b3164abf4caa4c74066ae6b88bcfa21998f62f7e411d","last_reissued_at":"2026-07-05T06:06:39.577871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:06:39.577871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Streaming Algorithms for High-Dimensional Robust Statistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.DS","authors_text":"Ankit Pensia, Daniel M. Kane, Ilias Diakonikolas, Thanasis Pittas","submitted_at":"2022-04-26T15:57:07Z","abstract_excerpt":"We study high-dimensional robust statistics tasks in the streaming model. A recent line of work obtained computationally efficient algorithms for a range of high-dimensional robust estimation tasks. Unfortunately, all previous algorithms require storing the entire dataset, incurring memory at least quadratic in the dimension. In this work, we develop the first efficient streaming algorithms for high-dimensional robust statistics with near-optimal memory requirements (up to logarithmic factors). Our main result is for the task of high-dimensional robust mean estimation in (a strengthening of) H"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.12399","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2204.12399/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2204.12399","created_at":"2026-07-05T06:06:39.577926+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.12399v2","created_at":"2026-07-05T06:06:39.577926+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.12399","created_at":"2026-07-05T06:06:39.577926+00:00"},{"alias_kind":"pith_short_12","alias_value":"U3WSXIZRJVPR","created_at":"2026-07-05T06:06:39.577926+00:00"},{"alias_kind":"pith_short_16","alias_value":"U3WSXIZRJVPRVZ7B","created_at":"2026-07-05T06:06:39.577926+00:00"},{"alias_kind":"pith_short_8","alias_value":"U3WSXIZR","created_at":"2026-07-05T06:06:39.577926+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U3WSXIZRJVPRVZ7BWMLEVP2MVJ","json":"https://pith.science/pith/U3WSXIZRJVPRVZ7BWMLEVP2MVJ.json","graph_json":"https://pith.science/api/pith-number/U3WSXIZRJVPRVZ7BWMLEVP2MVJ/graph.json","events_json":"https://pith.science/api/pith-number/U3WSXIZRJVPRVZ7BWMLEVP2MVJ/events.json","paper":"https://pith.science/paper/U3WSXIZR"},"agent_actions":{"view_html":"https://pith.science/pith/U3WSXIZRJVPRVZ7BWMLEVP2MVJ","download_json":"https://pith.science/pith/U3WSXIZRJVPRVZ7BWMLEVP2MVJ.json","view_paper":"https://pith.science/paper/U3WSXIZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.12399&json=true","fetch_graph":"https://pith.science/api/pith-number/U3WSXIZRJVPRVZ7BWMLEVP2MVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/U3WSXIZRJVPRVZ7BWMLEVP2MVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U3WSXIZRJVPRVZ7BWMLEVP2MVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U3WSXIZRJVPRVZ7BWMLEVP2MVJ/action/storage_attestation","attest_author":"https://pith.science/pith/U3WSXIZRJVPRVZ7BWMLEVP2MVJ/action/author_attestation","sign_citation":"https://pith.science/pith/U3WSXIZRJVPRVZ7BWMLEVP2MVJ/action/citation_signature","submit_replication":"https://pith.science/pith/U3WSXIZRJVPRVZ7BWMLEVP2MVJ/action/replication_record"}},"created_at":"2026-07-05T06:06:39.577926+00:00","updated_at":"2026-07-05T06:06:39.577926+00:00"}