{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4YNEVDHAFHS7JD4NHYTH4MDHE2","short_pith_number":"pith:4YNEVDHA","schema_version":"1.0","canonical_sha256":"e61a4a8ce029e5f48f8d3e267e30672687a8e14d1cdfd027d5f3a7ad2e337691","source":{"kind":"arxiv","id":"1901.01624","version":2},"attestation_state":"computed","paper":{"title":"Composite optimization for robust blind deconvolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"math.OC","authors_text":"Damek Davis, Dmitriy Drusvyatskiy, Mateo D\\'iaz, Vasileios Charisopoulos","submitted_at":"2019-01-06T23:08:47Z","abstract_excerpt":"The blind deconvolution problem seeks to recover a pair of vectors from a set of rank one bilinear measurements. We consider a natural nonsmooth formulation of the problem and show that under standard statistical assumptions, its moduli of weak convexity, sharpness, and Lipschitz continuity are all dimension independent. This phenomenon persists even when up to half of the measurements are corrupted by noise. Consequently, standard algorithms, such as the subgradient and prox-linear methods, converge at a rapid dimension-independent rate when initialized within constant relative error of the s"},"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":"1901.01624","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-01-06T23:08:47Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"7d38fa72cd5a38f168ec2cb5c1e91c28173e3f86a70c782e8d4f21fd4da006f1","abstract_canon_sha256":"2fef3eede76e6fa4b8aaa93fa84be4b321f3909b6691548e73436caf1337543a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:01.802298Z","signature_b64":"6M88aOTjvaE9OPpK8hVRZ6F6Z/gYsiZviTiKMpeUshJKTxXYwK1+5nbhiCUosO/065H0gN8X6yKEl5ldrv/tCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e61a4a8ce029e5f48f8d3e267e30672687a8e14d1cdfd027d5f3a7ad2e337691","last_reissued_at":"2026-05-17T23:56:01.801621Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:01.801621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Composite optimization for robust blind deconvolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"math.OC","authors_text":"Damek Davis, Dmitriy Drusvyatskiy, Mateo D\\'iaz, Vasileios Charisopoulos","submitted_at":"2019-01-06T23:08:47Z","abstract_excerpt":"The blind deconvolution problem seeks to recover a pair of vectors from a set of rank one bilinear measurements. We consider a natural nonsmooth formulation of the problem and show that under standard statistical assumptions, its moduli of weak convexity, sharpness, and Lipschitz continuity are all dimension independent. This phenomenon persists even when up to half of the measurements are corrupted by noise. Consequently, standard algorithms, such as the subgradient and prox-linear methods, converge at a rapid dimension-independent rate when initialized within constant relative error of the s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.01624","kind":"arxiv","version":2},"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":"1901.01624","created_at":"2026-05-17T23:56:01.801739+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.01624v2","created_at":"2026-05-17T23:56:01.801739+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.01624","created_at":"2026-05-17T23:56:01.801739+00:00"},{"alias_kind":"pith_short_12","alias_value":"4YNEVDHAFHS7","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"4YNEVDHAFHS7JD4N","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"4YNEVDHA","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.09547","citing_title":"Stochastic algorithms with geometric step decay converge linearly on sharp functions","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4YNEVDHAFHS7JD4NHYTH4MDHE2","json":"https://pith.science/pith/4YNEVDHAFHS7JD4NHYTH4MDHE2.json","graph_json":"https://pith.science/api/pith-number/4YNEVDHAFHS7JD4NHYTH4MDHE2/graph.json","events_json":"https://pith.science/api/pith-number/4YNEVDHAFHS7JD4NHYTH4MDHE2/events.json","paper":"https://pith.science/paper/4YNEVDHA"},"agent_actions":{"view_html":"https://pith.science/pith/4YNEVDHAFHS7JD4NHYTH4MDHE2","download_json":"https://pith.science/pith/4YNEVDHAFHS7JD4NHYTH4MDHE2.json","view_paper":"https://pith.science/paper/4YNEVDHA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.01624&json=true","fetch_graph":"https://pith.science/api/pith-number/4YNEVDHAFHS7JD4NHYTH4MDHE2/graph.json","fetch_events":"https://pith.science/api/pith-number/4YNEVDHAFHS7JD4NHYTH4MDHE2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4YNEVDHAFHS7JD4NHYTH4MDHE2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4YNEVDHAFHS7JD4NHYTH4MDHE2/action/storage_attestation","attest_author":"https://pith.science/pith/4YNEVDHAFHS7JD4NHYTH4MDHE2/action/author_attestation","sign_citation":"https://pith.science/pith/4YNEVDHAFHS7JD4NHYTH4MDHE2/action/citation_signature","submit_replication":"https://pith.science/pith/4YNEVDHAFHS7JD4NHYTH4MDHE2/action/replication_record"}},"created_at":"2026-05-17T23:56:01.801739+00:00","updated_at":"2026-05-17T23:56:01.801739+00:00"}