{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:5URVIPHY76VRDYPTOBNRJV7632","short_pith_number":"pith:5URVIPHY","schema_version":"1.0","canonical_sha256":"ed23543cf8ffab11e1f3705b14d7fede9c1635a2a559f68b4a16cb7235c9cbe0","source":{"kind":"arxiv","id":"1408.2044","version":1},"attestation_state":"computed","paper":{"title":"Matrix Coherence and the Nystrom Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Afshin Rostamizadeh, Ameet Talwalkar","submitted_at":"2014-08-09T05:40:28Z","abstract_excerpt":"The Nystrom method is an efficient technique used to speed up large-scale learning applications by generating low-rank approximations. Crucial to the performance of this technique is the assumption that a matrix can be well approximated by working exclusively with a subset of its columns. In this work we relate this assumption to the concept of matrix coherence, connecting coherence to the performance of the Nystrom method. Making use of related work in the compressed sensing and the matrix completion literature, we derive novel coherence-based bounds for the Nystrom method in the low-rank set"},"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":"1408.2044","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-08-09T05:40:28Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3c131f5d80dded57458dd5807946f4b1590be0c4d0b017488bf8bf114201f3e8","abstract_canon_sha256":"37edeb28d51e1fb6712f86ab4353b13c127287548e5ffb8edf5b20648bb56262"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:45:30.588766Z","signature_b64":"E7RN4dTwtONBRIzrJS0Lx0n+aPt0riJHSmqnm/SWi4rHRTqt41raGg6+T4dSteQJ632N6nEbbbKzSv2yCkVdDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed23543cf8ffab11e1f3705b14d7fede9c1635a2a559f68b4a16cb7235c9cbe0","last_reissued_at":"2026-05-18T02:45:30.588175Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:45:30.588175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Matrix Coherence and the Nystrom Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Afshin Rostamizadeh, Ameet Talwalkar","submitted_at":"2014-08-09T05:40:28Z","abstract_excerpt":"The Nystrom method is an efficient technique used to speed up large-scale learning applications by generating low-rank approximations. Crucial to the performance of this technique is the assumption that a matrix can be well approximated by working exclusively with a subset of its columns. In this work we relate this assumption to the concept of matrix coherence, connecting coherence to the performance of the Nystrom method. Making use of related work in the compressed sensing and the matrix completion literature, we derive novel coherence-based bounds for the Nystrom method in the low-rank set"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1408.2044","kind":"arxiv","version":1},"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":"1408.2044","created_at":"2026-05-18T02:45:30.588259+00:00"},{"alias_kind":"arxiv_version","alias_value":"1408.2044v1","created_at":"2026-05-18T02:45:30.588259+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1408.2044","created_at":"2026-05-18T02:45:30.588259+00:00"},{"alias_kind":"pith_short_12","alias_value":"5URVIPHY76VR","created_at":"2026-05-18T12:28:16.859392+00:00"},{"alias_kind":"pith_short_16","alias_value":"5URVIPHY76VRDYPT","created_at":"2026-05-18T12:28:16.859392+00:00"},{"alias_kind":"pith_short_8","alias_value":"5URVIPHY","created_at":"2026-05-18T12:28:16.859392+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.19250","citing_title":"Recovering Wasserstein Distance Matrices from Few Measurements","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5URVIPHY76VRDYPTOBNRJV7632","json":"https://pith.science/pith/5URVIPHY76VRDYPTOBNRJV7632.json","graph_json":"https://pith.science/api/pith-number/5URVIPHY76VRDYPTOBNRJV7632/graph.json","events_json":"https://pith.science/api/pith-number/5URVIPHY76VRDYPTOBNRJV7632/events.json","paper":"https://pith.science/paper/5URVIPHY"},"agent_actions":{"view_html":"https://pith.science/pith/5URVIPHY76VRDYPTOBNRJV7632","download_json":"https://pith.science/pith/5URVIPHY76VRDYPTOBNRJV7632.json","view_paper":"https://pith.science/paper/5URVIPHY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1408.2044&json=true","fetch_graph":"https://pith.science/api/pith-number/5URVIPHY76VRDYPTOBNRJV7632/graph.json","fetch_events":"https://pith.science/api/pith-number/5URVIPHY76VRDYPTOBNRJV7632/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5URVIPHY76VRDYPTOBNRJV7632/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5URVIPHY76VRDYPTOBNRJV7632/action/storage_attestation","attest_author":"https://pith.science/pith/5URVIPHY76VRDYPTOBNRJV7632/action/author_attestation","sign_citation":"https://pith.science/pith/5URVIPHY76VRDYPTOBNRJV7632/action/citation_signature","submit_replication":"https://pith.science/pith/5URVIPHY76VRDYPTOBNRJV7632/action/replication_record"}},"created_at":"2026-05-18T02:45:30.588259+00:00","updated_at":"2026-05-18T02:45:30.588259+00:00"}