{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AXAZTJ7KGO5VIFHJK3ONG6ZGJN","short_pith_number":"pith:AXAZTJ7K","schema_version":"1.0","canonical_sha256":"05c199a7ea33bb5414e956dcd37b264b750cc526bf65b6f83609c382ff0e30ef","source":{"kind":"arxiv","id":"2311.18810","version":1},"attestation_state":"computed","paper":{"title":"Convergence of Nonconvex PnP-ADMM with MMSE Denoisers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chicago Park, Shirin Shoushtari, Ulugbek S. Kamilov, Weijie Gan","submitted_at":"2023-11-30T18:52:47Z","abstract_excerpt":"Plug-and-Play Alternating Direction Method of Multipliers (PnP-ADMM) is a widely-used algorithm for solving inverse problems by integrating physical measurement models and convolutional neural network (CNN) priors. PnP-ADMM has been theoretically proven to converge for convex data-fidelity terms and nonexpansive CNNs. It has however been observed that PnP-ADMM often empirically converges even for expansive CNNs. This paper presents a theoretical explanation for the observed stability of PnP-ADMM based on the interpretation of the CNN prior as a minimum mean-squared error (MMSE) denoiser. Our e"},"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":"2311.18810","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-30T18:52:47Z","cross_cats_sorted":[],"title_canon_sha256":"e78a04d06e1de260a54a869676e7868316ba801a54cc694774ff8157c3d97654","abstract_canon_sha256":"041be5efa8277a8c99932f8a406dcb41ea774febd35d6ef66fa7721986bca9bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:46.879085Z","signature_b64":"pJ/OnjOX8QVZUtm6KqsWO595bhG+Aq013hy0IdS2/kDRq30Hvs8GSIEFP/FIrRqZwdivKMnK69TIKPUrimm4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05c199a7ea33bb5414e956dcd37b264b750cc526bf65b6f83609c382ff0e30ef","last_reissued_at":"2026-07-05T07:18:46.878644Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:46.878644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence of Nonconvex PnP-ADMM with MMSE Denoisers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chicago Park, Shirin Shoushtari, Ulugbek S. Kamilov, Weijie Gan","submitted_at":"2023-11-30T18:52:47Z","abstract_excerpt":"Plug-and-Play Alternating Direction Method of Multipliers (PnP-ADMM) is a widely-used algorithm for solving inverse problems by integrating physical measurement models and convolutional neural network (CNN) priors. PnP-ADMM has been theoretically proven to converge for convex data-fidelity terms and nonexpansive CNNs. It has however been observed that PnP-ADMM often empirically converges even for expansive CNNs. This paper presents a theoretical explanation for the observed stability of PnP-ADMM based on the interpretation of the CNN prior as a minimum mean-squared error (MMSE) denoiser. Our e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.18810","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2311.18810/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":"2311.18810","created_at":"2026-07-05T07:18:46.878698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.18810v1","created_at":"2026-07-05T07:18:46.878698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.18810","created_at":"2026-07-05T07:18:46.878698+00:00"},{"alias_kind":"pith_short_12","alias_value":"AXAZTJ7KGO5V","created_at":"2026-07-05T07:18:46.878698+00:00"},{"alias_kind":"pith_short_16","alias_value":"AXAZTJ7KGO5VIFHJ","created_at":"2026-07-05T07:18:46.878698+00:00"},{"alias_kind":"pith_short_8","alias_value":"AXAZTJ7K","created_at":"2026-07-05T07:18:46.878698+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/AXAZTJ7KGO5VIFHJK3ONG6ZGJN","json":"https://pith.science/pith/AXAZTJ7KGO5VIFHJK3ONG6ZGJN.json","graph_json":"https://pith.science/api/pith-number/AXAZTJ7KGO5VIFHJK3ONG6ZGJN/graph.json","events_json":"https://pith.science/api/pith-number/AXAZTJ7KGO5VIFHJK3ONG6ZGJN/events.json","paper":"https://pith.science/paper/AXAZTJ7K"},"agent_actions":{"view_html":"https://pith.science/pith/AXAZTJ7KGO5VIFHJK3ONG6ZGJN","download_json":"https://pith.science/pith/AXAZTJ7KGO5VIFHJK3ONG6ZGJN.json","view_paper":"https://pith.science/paper/AXAZTJ7K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.18810&json=true","fetch_graph":"https://pith.science/api/pith-number/AXAZTJ7KGO5VIFHJK3ONG6ZGJN/graph.json","fetch_events":"https://pith.science/api/pith-number/AXAZTJ7KGO5VIFHJK3ONG6ZGJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AXAZTJ7KGO5VIFHJK3ONG6ZGJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AXAZTJ7KGO5VIFHJK3ONG6ZGJN/action/storage_attestation","attest_author":"https://pith.science/pith/AXAZTJ7KGO5VIFHJK3ONG6ZGJN/action/author_attestation","sign_citation":"https://pith.science/pith/AXAZTJ7KGO5VIFHJK3ONG6ZGJN/action/citation_signature","submit_replication":"https://pith.science/pith/AXAZTJ7KGO5VIFHJK3ONG6ZGJN/action/replication_record"}},"created_at":"2026-07-05T07:18:46.878698+00:00","updated_at":"2026-07-05T07:18:46.878698+00:00"}