{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:QOYIFRD7GYVNVQCMGGQ3C3CPQR","short_pith_number":"pith:QOYIFRD7","schema_version":"1.0","canonical_sha256":"83b082c47f362adac04c31a1b16c4f8474b9b1ad0b2d74204b41eaca976f9220","source":{"kind":"arxiv","id":"1510.04747","version":7},"attestation_state":"computed","paper":{"title":"Tensor vs Matrix Methods: Robust Tensor Decomposition under Block Sparse Perturbations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Animashree Anandkumar, Prateek Jain, U. N. Niranjan, Yang Shi","submitted_at":"2015-10-15T23:40:13Z","abstract_excerpt":"Robust tensor CP decomposition involves decomposing a tensor into low rank and sparse components. We propose a novel non-convex iterative algorithm with guaranteed recovery. It alternates between low-rank CP decomposition through gradient ascent (a variant of the tensor power method), and hard thresholding of the residual. We prove convergence to the globally optimal solution under natural incoherence conditions on the low rank component, and bounded level of sparse perturbations. We compare our method with natural baselines which apply robust matrix PCA either to the {\\em flattened} tensor, o"},"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":"1510.04747","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-10-15T23:40:13Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"71bad866614df3835eeb35cf34065ba83e1e2f64685a7153146a05928102f649","abstract_canon_sha256":"28791394f5f9ee79932f25631d0a40f314e3c984219f1b3b7583d29f34953d0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:16:09.593145Z","signature_b64":"FgezHC7Svmd2qERsS+4Jqb+lRVcnf/7DaQqMo2ogYD0VyTBAmOA2KwqN+CsdRT7vUsUlh5T18OrWHlWp1IqtBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83b082c47f362adac04c31a1b16c4f8474b9b1ad0b2d74204b41eaca976f9220","last_reissued_at":"2026-05-18T01:16:09.592488Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:16:09.592488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tensor vs Matrix Methods: Robust Tensor Decomposition under Block Sparse Perturbations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Animashree Anandkumar, Prateek Jain, U. N. Niranjan, Yang Shi","submitted_at":"2015-10-15T23:40:13Z","abstract_excerpt":"Robust tensor CP decomposition involves decomposing a tensor into low rank and sparse components. We propose a novel non-convex iterative algorithm with guaranteed recovery. It alternates between low-rank CP decomposition through gradient ascent (a variant of the tensor power method), and hard thresholding of the residual. We prove convergence to the globally optimal solution under natural incoherence conditions on the low rank component, and bounded level of sparse perturbations. We compare our method with natural baselines which apply robust matrix PCA either to the {\\em flattened} tensor, o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.04747","kind":"arxiv","version":7},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1510.04747","created_at":"2026-05-18T01:16:09.592599+00:00"},{"alias_kind":"arxiv_version","alias_value":"1510.04747v7","created_at":"2026-05-18T01:16:09.592599+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.04747","created_at":"2026-05-18T01:16:09.592599+00:00"},{"alias_kind":"pith_short_12","alias_value":"QOYIFRD7GYVN","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_16","alias_value":"QOYIFRD7GYVNVQCM","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_8","alias_value":"QOYIFRD7","created_at":"2026-05-18T12:29:37.295048+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/QOYIFRD7GYVNVQCMGGQ3C3CPQR","json":"https://pith.science/pith/QOYIFRD7GYVNVQCMGGQ3C3CPQR.json","graph_json":"https://pith.science/api/pith-number/QOYIFRD7GYVNVQCMGGQ3C3CPQR/graph.json","events_json":"https://pith.science/api/pith-number/QOYIFRD7GYVNVQCMGGQ3C3CPQR/events.json","paper":"https://pith.science/paper/QOYIFRD7"},"agent_actions":{"view_html":"https://pith.science/pith/QOYIFRD7GYVNVQCMGGQ3C3CPQR","download_json":"https://pith.science/pith/QOYIFRD7GYVNVQCMGGQ3C3CPQR.json","view_paper":"https://pith.science/paper/QOYIFRD7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1510.04747&json=true","fetch_graph":"https://pith.science/api/pith-number/QOYIFRD7GYVNVQCMGGQ3C3CPQR/graph.json","fetch_events":"https://pith.science/api/pith-number/QOYIFRD7GYVNVQCMGGQ3C3CPQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QOYIFRD7GYVNVQCMGGQ3C3CPQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QOYIFRD7GYVNVQCMGGQ3C3CPQR/action/storage_attestation","attest_author":"https://pith.science/pith/QOYIFRD7GYVNVQCMGGQ3C3CPQR/action/author_attestation","sign_citation":"https://pith.science/pith/QOYIFRD7GYVNVQCMGGQ3C3CPQR/action/citation_signature","submit_replication":"https://pith.science/pith/QOYIFRD7GYVNVQCMGGQ3C3CPQR/action/replication_record"}},"created_at":"2026-05-18T01:16:09.592599+00:00","updated_at":"2026-05-18T01:16:09.592599+00:00"}