{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BOOTDZKZXUG3BKDA76M3SMCSXR","short_pith_number":"pith:BOOTDZKZ","schema_version":"1.0","canonical_sha256":"0b9d31e559bd0db0a860ff99b93052bc54e3c4ca89dbabe888ec98b20455c6c8","source":{"kind":"arxiv","id":"2209.10675","version":3},"attestation_state":"computed","paper":{"title":"A Validation Approach to Over-parameterized Matrix and Image Recovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV","stat.ML"],"primary_cat":"math.OC","authors_text":"Jinxin Zhou, Lijun Ding, Liwei Jiang, Zhen Qin, Zhihui Zhu","submitted_at":"2022-09-21T22:01:23Z","abstract_excerpt":"This paper studies the problem of recovering a low-rank matrix from several noisy random linear measurements. We consider the setting where the rank of the ground-truth matrix is unknown a priori and use an objective function built from a rank-overspecified factored representation of the matrix variable, where the global optimal solutions overfit and do not correspond to the underlying ground truth. We then solve the associated nonconvex problem using gradient descent with small random initialization. We show that as long as the measurement operators satisfy the restricted isometry property (R"},"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":"2209.10675","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-09-21T22:01:23Z","cross_cats_sorted":["cs.LG","eess.IV","stat.ML"],"title_canon_sha256":"58615591febed4e16601feade8b14eeea8a597939489459536393dd12bc1b4cc","abstract_canon_sha256":"f1b200b240a28dcfb2dac05061f3802206f22427700abab79bfa4616945fe654"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:26.795950Z","signature_b64":"wjktuZ6bKLq/eb+5D+fsNdTivu1Z83heoODNPPT53QTeAxe2hDJJczpTNMEamBzeE7hpluP/6g27b/gv1FRVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b9d31e559bd0db0a860ff99b93052bc54e3c4ca89dbabe888ec98b20455c6c8","last_reissued_at":"2026-07-05T11:43:26.795473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:26.795473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Validation Approach to Over-parameterized Matrix and Image Recovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV","stat.ML"],"primary_cat":"math.OC","authors_text":"Jinxin Zhou, Lijun Ding, Liwei Jiang, Zhen Qin, Zhihui Zhu","submitted_at":"2022-09-21T22:01:23Z","abstract_excerpt":"This paper studies the problem of recovering a low-rank matrix from several noisy random linear measurements. We consider the setting where the rank of the ground-truth matrix is unknown a priori and use an objective function built from a rank-overspecified factored representation of the matrix variable, where the global optimal solutions overfit and do not correspond to the underlying ground truth. We then solve the associated nonconvex problem using gradient descent with small random initialization. We show that as long as the measurement operators satisfy the restricted isometry property (R"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.10675","kind":"arxiv","version":3},"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/2209.10675/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":"2209.10675","created_at":"2026-07-05T11:43:26.795549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.10675v3","created_at":"2026-07-05T11:43:26.795549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.10675","created_at":"2026-07-05T11:43:26.795549+00:00"},{"alias_kind":"pith_short_12","alias_value":"BOOTDZKZXUG3","created_at":"2026-07-05T11:43:26.795549+00:00"},{"alias_kind":"pith_short_16","alias_value":"BOOTDZKZXUG3BKDA","created_at":"2026-07-05T11:43:26.795549+00:00"},{"alias_kind":"pith_short_8","alias_value":"BOOTDZKZ","created_at":"2026-07-05T11:43:26.795549+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08535","citing_title":"Structured Variational $D$-Decomposition for Accurate and Stable Low-Rank Approximation","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BOOTDZKZXUG3BKDA76M3SMCSXR","json":"https://pith.science/pith/BOOTDZKZXUG3BKDA76M3SMCSXR.json","graph_json":"https://pith.science/api/pith-number/BOOTDZKZXUG3BKDA76M3SMCSXR/graph.json","events_json":"https://pith.science/api/pith-number/BOOTDZKZXUG3BKDA76M3SMCSXR/events.json","paper":"https://pith.science/paper/BOOTDZKZ"},"agent_actions":{"view_html":"https://pith.science/pith/BOOTDZKZXUG3BKDA76M3SMCSXR","download_json":"https://pith.science/pith/BOOTDZKZXUG3BKDA76M3SMCSXR.json","view_paper":"https://pith.science/paper/BOOTDZKZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.10675&json=true","fetch_graph":"https://pith.science/api/pith-number/BOOTDZKZXUG3BKDA76M3SMCSXR/graph.json","fetch_events":"https://pith.science/api/pith-number/BOOTDZKZXUG3BKDA76M3SMCSXR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BOOTDZKZXUG3BKDA76M3SMCSXR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BOOTDZKZXUG3BKDA76M3SMCSXR/action/storage_attestation","attest_author":"https://pith.science/pith/BOOTDZKZXUG3BKDA76M3SMCSXR/action/author_attestation","sign_citation":"https://pith.science/pith/BOOTDZKZXUG3BKDA76M3SMCSXR/action/citation_signature","submit_replication":"https://pith.science/pith/BOOTDZKZXUG3BKDA76M3SMCSXR/action/replication_record"}},"created_at":"2026-07-05T11:43:26.795549+00:00","updated_at":"2026-07-05T11:43:26.795549+00:00"}