{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:MNHO3LZXTLFTMBJLTT7WNWQS2I","short_pith_number":"pith:MNHO3LZX","schema_version":"1.0","canonical_sha256":"634eedaf379acb36052b9cff66da12d2370b8fdf439790e1aa79b8488732515d","source":{"kind":"arxiv","id":"1608.05995","version":5},"attestation_state":"computed","paper":{"title":"A Non-convex One-Pass Framework for Generalized Factorization Machine and Rank-One Matrix Sensing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jieping Ye, Ming Lin","submitted_at":"2016-08-21T20:28:29Z","abstract_excerpt":"We develop an efficient alternating framework for learning a generalized version of Factorization Machine (gFM) on steaming data with provable guarantees. When the instances are sampled from $d$ dimensional random Gaussian vectors and the target second order coefficient matrix in gFM is of rank $k$, our algorithm converges linearly, achieves $O(\\epsilon)$ recovery error after retrieving $O(k^{3}d\\log(1/\\epsilon))$ training instances, consumes $O(kd)$ memory in one-pass of dataset and only requires matrix-vector product operations in each iteration. The key ingredient of our framework is a cons"},"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":"1608.05995","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-08-21T20:28:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c7bfc5b31edf79700b5e39bae26be0bb9acc03efa17cb0c2b7afb4aec0af3c71","abstract_canon_sha256":"627bd66e161bfd68a8138f73dfb6e56cc089223c5e3d09a7633a3da859a35276"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:01:15.428949Z","signature_b64":"G3QwPHGDo2fDTFhguDzsPI7t0uM50pqvPhbooFOIh6eU+YasqrWBE09wzZ+b8iUEjsEFqVu0dTjfCQcudm29Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"634eedaf379acb36052b9cff66da12d2370b8fdf439790e1aa79b8488732515d","last_reissued_at":"2026-05-18T01:01:15.428162Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:01:15.428162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Non-convex One-Pass Framework for Generalized Factorization Machine and Rank-One Matrix Sensing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jieping Ye, Ming Lin","submitted_at":"2016-08-21T20:28:29Z","abstract_excerpt":"We develop an efficient alternating framework for learning a generalized version of Factorization Machine (gFM) on steaming data with provable guarantees. When the instances are sampled from $d$ dimensional random Gaussian vectors and the target second order coefficient matrix in gFM is of rank $k$, our algorithm converges linearly, achieves $O(\\epsilon)$ recovery error after retrieving $O(k^{3}d\\log(1/\\epsilon))$ training instances, consumes $O(kd)$ memory in one-pass of dataset and only requires matrix-vector product operations in each iteration. The key ingredient of our framework is a cons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.05995","kind":"arxiv","version":5},"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":"1608.05995","created_at":"2026-05-18T01:01:15.428301+00:00"},{"alias_kind":"arxiv_version","alias_value":"1608.05995v5","created_at":"2026-05-18T01:01:15.428301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.05995","created_at":"2026-05-18T01:01:15.428301+00:00"},{"alias_kind":"pith_short_12","alias_value":"MNHO3LZXTLFT","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_16","alias_value":"MNHO3LZXTLFTMBJL","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_8","alias_value":"MNHO3LZX","created_at":"2026-05-18T12:30:32.724797+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/MNHO3LZXTLFTMBJLTT7WNWQS2I","json":"https://pith.science/pith/MNHO3LZXTLFTMBJLTT7WNWQS2I.json","graph_json":"https://pith.science/api/pith-number/MNHO3LZXTLFTMBJLTT7WNWQS2I/graph.json","events_json":"https://pith.science/api/pith-number/MNHO3LZXTLFTMBJLTT7WNWQS2I/events.json","paper":"https://pith.science/paper/MNHO3LZX"},"agent_actions":{"view_html":"https://pith.science/pith/MNHO3LZXTLFTMBJLTT7WNWQS2I","download_json":"https://pith.science/pith/MNHO3LZXTLFTMBJLTT7WNWQS2I.json","view_paper":"https://pith.science/paper/MNHO3LZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1608.05995&json=true","fetch_graph":"https://pith.science/api/pith-number/MNHO3LZXTLFTMBJLTT7WNWQS2I/graph.json","fetch_events":"https://pith.science/api/pith-number/MNHO3LZXTLFTMBJLTT7WNWQS2I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MNHO3LZXTLFTMBJLTT7WNWQS2I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MNHO3LZXTLFTMBJLTT7WNWQS2I/action/storage_attestation","attest_author":"https://pith.science/pith/MNHO3LZXTLFTMBJLTT7WNWQS2I/action/author_attestation","sign_citation":"https://pith.science/pith/MNHO3LZXTLFTMBJLTT7WNWQS2I/action/citation_signature","submit_replication":"https://pith.science/pith/MNHO3LZXTLFTMBJLTT7WNWQS2I/action/replication_record"}},"created_at":"2026-05-18T01:01:15.428301+00:00","updated_at":"2026-05-18T01:01:15.428301+00:00"}