{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZE4R75XMPHJLNML2HNV54A5KS2","short_pith_number":"pith:ZE4R75XM","schema_version":"1.0","canonical_sha256":"c9391ff6ec79d2b6b17a3b6bde03aa969fb6c1c40200a86fc494a63acb96436f","source":{"kind":"arxiv","id":"1908.10776","version":3},"attestation_state":"computed","paper":{"title":"A Nonconvex Approach for Exact and Efficient Multichannel Sparse Blind Deconvolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV","math.OC","stat.ML"],"primary_cat":"eess.SP","authors_text":"Qing Qu, Xiao Li, Zhihui Zhu","submitted_at":"2019-08-28T15:25:54Z","abstract_excerpt":"We study the multi-channel sparse blind deconvolution (MCS-BD) problem, whose task is to simultaneously recover a kernel $\\mathbf a$ and multiple sparse inputs $\\{\\mathbf x_i\\}_{i=1}^p$ from their circulant convolution $\\mathbf y_i = \\mathbf a \\circledast \\mathbf x_i $ ($i=1,\\cdots,p$). We formulate the task as a nonconvex optimization problem over the sphere. Under mild statistical assumptions of the data, we prove that the vanilla Riemannian gradient descent (RGD) method, with random initializations, provably recovers both the kernel $\\mathbf a$ and the signals $\\{\\mathbf x_i\\}_{i=1}^p$ up t"},"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":"1908.10776","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SP","submitted_at":"2019-08-28T15:25:54Z","cross_cats_sorted":["cs.LG","eess.IV","math.OC","stat.ML"],"title_canon_sha256":"ae4f24a0c748a070d6f21f416514f168dba82a0342c7a905e75ad2ae107d1f54","abstract_canon_sha256":"d2d5ca8cd929de49c334bef161de43953ce13cab495288ba867ccd0ef174b8a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:44:39.833627Z","signature_b64":"lzIukxrvaPlfu7QLK2JqayrnxnqMh22guTsyWpGak1/Y/WWm4fe74LTVAqorDmE44/ZDA+lGc0iXXH2TIEBZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9391ff6ec79d2b6b17a3b6bde03aa969fb6c1c40200a86fc494a63acb96436f","last_reissued_at":"2026-07-05T00:44:39.833280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:44:39.833280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Nonconvex Approach for Exact and Efficient Multichannel Sparse Blind Deconvolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV","math.OC","stat.ML"],"primary_cat":"eess.SP","authors_text":"Qing Qu, Xiao Li, Zhihui Zhu","submitted_at":"2019-08-28T15:25:54Z","abstract_excerpt":"We study the multi-channel sparse blind deconvolution (MCS-BD) problem, whose task is to simultaneously recover a kernel $\\mathbf a$ and multiple sparse inputs $\\{\\mathbf x_i\\}_{i=1}^p$ from their circulant convolution $\\mathbf y_i = \\mathbf a \\circledast \\mathbf x_i $ ($i=1,\\cdots,p$). We formulate the task as a nonconvex optimization problem over the sphere. Under mild statistical assumptions of the data, we prove that the vanilla Riemannian gradient descent (RGD) method, with random initializations, provably recovers both the kernel $\\mathbf a$ and the signals $\\{\\mathbf x_i\\}_{i=1}^p$ up t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.10776","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/1908.10776/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":"1908.10776","created_at":"2026-07-05T00:44:39.833342+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.10776v3","created_at":"2026-07-05T00:44:39.833342+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.10776","created_at":"2026-07-05T00:44:39.833342+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZE4R75XMPHJL","created_at":"2026-07-05T00:44:39.833342+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZE4R75XMPHJLNML2","created_at":"2026-07-05T00:44:39.833342+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZE4R75XM","created_at":"2026-07-05T00:44:39.833342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.10959","citing_title":"Short-and-Sparse Deconvolution -- A Geometric Approach","ref_index":83,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZE4R75XMPHJLNML2HNV54A5KS2","json":"https://pith.science/pith/ZE4R75XMPHJLNML2HNV54A5KS2.json","graph_json":"https://pith.science/api/pith-number/ZE4R75XMPHJLNML2HNV54A5KS2/graph.json","events_json":"https://pith.science/api/pith-number/ZE4R75XMPHJLNML2HNV54A5KS2/events.json","paper":"https://pith.science/paper/ZE4R75XM"},"agent_actions":{"view_html":"https://pith.science/pith/ZE4R75XMPHJLNML2HNV54A5KS2","download_json":"https://pith.science/pith/ZE4R75XMPHJLNML2HNV54A5KS2.json","view_paper":"https://pith.science/paper/ZE4R75XM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.10776&json=true","fetch_graph":"https://pith.science/api/pith-number/ZE4R75XMPHJLNML2HNV54A5KS2/graph.json","fetch_events":"https://pith.science/api/pith-number/ZE4R75XMPHJLNML2HNV54A5KS2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZE4R75XMPHJLNML2HNV54A5KS2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZE4R75XMPHJLNML2HNV54A5KS2/action/storage_attestation","attest_author":"https://pith.science/pith/ZE4R75XMPHJLNML2HNV54A5KS2/action/author_attestation","sign_citation":"https://pith.science/pith/ZE4R75XMPHJLNML2HNV54A5KS2/action/citation_signature","submit_replication":"https://pith.science/pith/ZE4R75XMPHJLNML2HNV54A5KS2/action/replication_record"}},"created_at":"2026-07-05T00:44:39.833342+00:00","updated_at":"2026-07-05T00:44:39.833342+00:00"}