{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:QFXHUMZJTX3NI7SBOYKJR23MSX","short_pith_number":"pith:QFXHUMZJ","schema_version":"1.0","canonical_sha256":"816e7a33299df6d47e41761498eb6c95fc6633f3bbe27dbd2f002906f16030e0","source":{"kind":"arxiv","id":"1507.05950","version":1},"attestation_state":"computed","paper":{"title":"On the Worst-Case Approximability of Sparse PCA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","cs.DS","cs.LG"],"primary_cat":"stat.ML","authors_text":"Aviad Rubinstein, Dimitris Papailiopoulos, Siu On Chan","submitted_at":"2015-07-21T19:34:32Z","abstract_excerpt":"It is well known that Sparse PCA (Sparse Principal Component Analysis) is NP-hard to solve exactly on worst-case instances. What is the complexity of solving Sparse PCA approximately? Our contributions include: 1) a simple and efficient algorithm that achieves an $n^{-1/3}$-approximation; 2) NP-hardness of approximation to within $(1-\\varepsilon)$, for some small constant $\\varepsilon > 0$; 3) SSE-hardness of approximation to within any constant factor; and 4) an $\\exp\\exp\\left(\\Omega\\left(\\sqrt{\\log \\log n}\\right)\\right)$ (\"quasi-quasi-polynomial\") gap for the standard semidefinite program."},"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":"1507.05950","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-07-21T19:34:32Z","cross_cats_sorted":["cs.CC","cs.DS","cs.LG"],"title_canon_sha256":"4129b9c6719a9785d915b164f38dc96a67d8f4fcbfc8e0ff4d604bf9d8de8451","abstract_canon_sha256":"acc953ad6d0520243bfe44a9a255e822a3ab692a371a2d99c044ed17706da69c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:36:32.064368Z","signature_b64":"ov1wlP9RbTbHMYF1WnyDZOlWkzYlu58M3zbYxI959P60MT4Yt+OOtvGwMS4V7g30Bh5NsANVv0F4mwW0u7bYBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"816e7a33299df6d47e41761498eb6c95fc6633f3bbe27dbd2f002906f16030e0","last_reissued_at":"2026-05-18T01:36:32.063708Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:36:32.063708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Worst-Case Approximability of Sparse PCA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","cs.DS","cs.LG"],"primary_cat":"stat.ML","authors_text":"Aviad Rubinstein, Dimitris Papailiopoulos, Siu On Chan","submitted_at":"2015-07-21T19:34:32Z","abstract_excerpt":"It is well known that Sparse PCA (Sparse Principal Component Analysis) is NP-hard to solve exactly on worst-case instances. What is the complexity of solving Sparse PCA approximately? Our contributions include: 1) a simple and efficient algorithm that achieves an $n^{-1/3}$-approximation; 2) NP-hardness of approximation to within $(1-\\varepsilon)$, for some small constant $\\varepsilon > 0$; 3) SSE-hardness of approximation to within any constant factor; and 4) an $\\exp\\exp\\left(\\Omega\\left(\\sqrt{\\log \\log n}\\right)\\right)$ (\"quasi-quasi-polynomial\") gap for the standard semidefinite program."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.05950","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":"1507.05950","created_at":"2026-05-18T01:36:32.063812+00:00"},{"alias_kind":"arxiv_version","alias_value":"1507.05950v1","created_at":"2026-05-18T01:36:32.063812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.05950","created_at":"2026-05-18T01:36:32.063812+00:00"},{"alias_kind":"pith_short_12","alias_value":"QFXHUMZJTX3N","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_16","alias_value":"QFXHUMZJTX3NI7SB","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_8","alias_value":"QFXHUMZJ","created_at":"2026-05-18T12:29:37.295048+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09148","citing_title":"A Randomized Algorithm for Sparse PCA based on the Basic SDP Relaxation","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QFXHUMZJTX3NI7SBOYKJR23MSX","json":"https://pith.science/pith/QFXHUMZJTX3NI7SBOYKJR23MSX.json","graph_json":"https://pith.science/api/pith-number/QFXHUMZJTX3NI7SBOYKJR23MSX/graph.json","events_json":"https://pith.science/api/pith-number/QFXHUMZJTX3NI7SBOYKJR23MSX/events.json","paper":"https://pith.science/paper/QFXHUMZJ"},"agent_actions":{"view_html":"https://pith.science/pith/QFXHUMZJTX3NI7SBOYKJR23MSX","download_json":"https://pith.science/pith/QFXHUMZJTX3NI7SBOYKJR23MSX.json","view_paper":"https://pith.science/paper/QFXHUMZJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1507.05950&json=true","fetch_graph":"https://pith.science/api/pith-number/QFXHUMZJTX3NI7SBOYKJR23MSX/graph.json","fetch_events":"https://pith.science/api/pith-number/QFXHUMZJTX3NI7SBOYKJR23MSX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QFXHUMZJTX3NI7SBOYKJR23MSX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QFXHUMZJTX3NI7SBOYKJR23MSX/action/storage_attestation","attest_author":"https://pith.science/pith/QFXHUMZJTX3NI7SBOYKJR23MSX/action/author_attestation","sign_citation":"https://pith.science/pith/QFXHUMZJTX3NI7SBOYKJR23MSX/action/citation_signature","submit_replication":"https://pith.science/pith/QFXHUMZJTX3NI7SBOYKJR23MSX/action/replication_record"}},"created_at":"2026-05-18T01:36:32.063812+00:00","updated_at":"2026-05-18T01:36:32.063812+00:00"}