{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BVACLJH6GKTCIBCA6DJ22RDKI3","short_pith_number":"pith:BVACLJH6","schema_version":"1.0","canonical_sha256":"0d4025a4fe32a6240440f0d3ad446a46e5f4c9795bad2d393266281c8f353392","source":{"kind":"arxiv","id":"2510.27211","version":7},"attestation_state":"computed","paper":{"title":"Nonasymptotic Convergence Rates for Plug-and-Play Methods With MMSE Denoisers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"The MMSE denoiser under Gaussian noise corresponds to a 1-weakly convex regularizer given by an upper Moreau envelope of the negative log-marginal density, which yields the first sublinear convergence rates for plug-and-play proximal grad","cross_cats":["eess.SP","stat.ML"],"primary_cat":"math.OC","authors_text":"Henry Pritchard, Rahul Parhi","submitted_at":"2025-10-31T06:12:49Z","abstract_excerpt":"It is known that the minimum-mean-squared-error (MMSE) denoiser under Gaussian noise can be written as a proximal operator, which suffices for asymptotic convergence of plug-and-play (PnP) methods but does not reveal the structure of the induced regularizer or give convergence rates. We show that the MMSE denoiser corresponds to a regularizer that can be written explicitly as an upper Moreau envelope of the negative log-marginal density, which in turn implies that the regularizer is 1-weakly convex. Using this property, we derive (to the best of our knowledge) the first sublinear convergence g"},"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":true},"canonical_record":{"source":{"id":"2510.27211","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-10-31T06:12:49Z","cross_cats_sorted":["eess.SP","stat.ML"],"title_canon_sha256":"d41493dca1126beb10d36d1916e60112686faac6c33662d523c88ee9443cb719","abstract_canon_sha256":"b7b329f9f7f8d23b6251197e581f62e929e7d70b5260fa9025da878b1b62b810"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:09:51.984646Z","signature_b64":"ZIgo5yxmtXC/ZpExwZ9SglQ07MJ6uvrAQq9ad677eJPhy9Tc7BpzEsGEErS0w/y1nFjotRBzj+ZFOlcXwCkNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d4025a4fe32a6240440f0d3ad446a46e5f4c9795bad2d393266281c8f353392","last_reissued_at":"2026-06-19T16:09:51.984059Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:09:51.984059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nonasymptotic Convergence Rates for Plug-and-Play Methods With MMSE Denoisers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"The MMSE denoiser under Gaussian noise corresponds to a 1-weakly convex regularizer given by an upper Moreau envelope of the negative log-marginal density, which yields the first sublinear convergence rates for plug-and-play proximal grad","cross_cats":["eess.SP","stat.ML"],"primary_cat":"math.OC","authors_text":"Henry Pritchard, Rahul Parhi","submitted_at":"2025-10-31T06:12:49Z","abstract_excerpt":"It is known that the minimum-mean-squared-error (MMSE) denoiser under Gaussian noise can be written as a proximal operator, which suffices for asymptotic convergence of plug-and-play (PnP) methods but does not reveal the structure of the induced regularizer or give convergence rates. We show that the MMSE denoiser corresponds to a regularizer that can be written explicitly as an upper Moreau envelope of the negative log-marginal density, which in turn implies that the regularizer is 1-weakly convex. Using this property, we derive (to the best of our knowledge) the first sublinear convergence g"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We show that the MMSE denoiser corresponds to a regularizer that can be written explicitly as an upper Moreau envelope of the negative log-marginal density, which in turn implies that the regularizer is 1-weakly convex. Using this property, we derive the first sublinear convergence guarantee for PnP proximal gradient descent with an MMSE denoiser.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The derivation assumes the noise is exactly Gaussian and that the MMSE denoiser is applied without any additional approximation or clipping; if the actual noise deviates from this model or if the denoiser is replaced by a learned network that only approximates the MMSE operator, the weak-convexity and rate guarantees no longer hold directly (see abstract and the proximal-operator equivalence stated in the introduction).","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MMSE denoisers correspond to 1-weakly convex regularizers via upper Moreau envelopes of negative log-marginals, enabling the first sublinear convergence rates for PnP proximal gradient descent.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"The MMSE denoiser under Gaussian noise corresponds to a 1-weakly convex regularizer given by an upper Moreau envelope of the negative log-marginal density, which yields the first sublinear convergence rates for plug-and-play proximal grad","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"954b757783bb55ac136cca34254f8fe324fc9626448e07548e837d984c17e2a1"},"source":{"id":"2510.27211","kind":"arxiv","version":7},"verdict":{"id":"88d7ccfa-6a77-443f-a86b-389c918d8860","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-18T03:34:56.233495Z","strongest_claim":"We show that the MMSE denoiser corresponds to a regularizer that can be written explicitly as an upper Moreau envelope of the negative log-marginal density, which in turn implies that the regularizer is 1-weakly convex. Using this property, we derive the first sublinear convergence guarantee for PnP proximal gradient descent with an MMSE denoiser.","one_line_summary":"MMSE denoisers correspond to 1-weakly convex regularizers via upper Moreau envelopes of negative log-marginals, enabling the first sublinear convergence rates for PnP proximal gradient descent.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The derivation assumes the noise is exactly Gaussian and that the MMSE denoiser is applied without any additional approximation or clipping; if the actual noise deviates from this model or if the denoiser is replaced by a learned network that only approximates the MMSE operator, the weak-convexity and rate guarantees no longer hold directly (see abstract and the proximal-operator equivalence stated in the introduction).","pith_extraction_headline":"The MMSE denoiser under Gaussian noise corresponds to a 1-weakly convex regularizer given by an upper Moreau envelope of the negative log-marginal density, which yields the first sublinear convergence rates for plug-and-play proximal grad"},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2510.27211/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":2,"snapshot_sha256":"06041956e969190d6742826d1ed79fa4dd6dd408be486674d710b036b3b67cbd"},"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":"2510.27211","created_at":"2026-06-19T16:09:51.984132+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.27211v7","created_at":"2026-06-19T16:09:51.984132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.27211","created_at":"2026-06-19T16:09:51.984132+00:00"},{"alias_kind":"pith_short_12","alias_value":"BVACLJH6GKTC","created_at":"2026-06-19T16:09:51.984132+00:00"},{"alias_kind":"pith_short_16","alias_value":"BVACLJH6GKTCIBCA","created_at":"2026-06-19T16:09:51.984132+00:00"},{"alias_kind":"pith_short_8","alias_value":"BVACLJH6","created_at":"2026-06-19T16:09:51.984132+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BVACLJH6GKTCIBCA6DJ22RDKI3","json":"https://pith.science/pith/BVACLJH6GKTCIBCA6DJ22RDKI3.json","graph_json":"https://pith.science/api/pith-number/BVACLJH6GKTCIBCA6DJ22RDKI3/graph.json","events_json":"https://pith.science/api/pith-number/BVACLJH6GKTCIBCA6DJ22RDKI3/events.json","paper":"https://pith.science/paper/BVACLJH6"},"agent_actions":{"view_html":"https://pith.science/pith/BVACLJH6GKTCIBCA6DJ22RDKI3","download_json":"https://pith.science/pith/BVACLJH6GKTCIBCA6DJ22RDKI3.json","view_paper":"https://pith.science/paper/BVACLJH6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.27211&json=true","fetch_graph":"https://pith.science/api/pith-number/BVACLJH6GKTCIBCA6DJ22RDKI3/graph.json","fetch_events":"https://pith.science/api/pith-number/BVACLJH6GKTCIBCA6DJ22RDKI3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BVACLJH6GKTCIBCA6DJ22RDKI3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BVACLJH6GKTCIBCA6DJ22RDKI3/action/storage_attestation","attest_author":"https://pith.science/pith/BVACLJH6GKTCIBCA6DJ22RDKI3/action/author_attestation","sign_citation":"https://pith.science/pith/BVACLJH6GKTCIBCA6DJ22RDKI3/action/citation_signature","submit_replication":"https://pith.science/pith/BVACLJH6GKTCIBCA6DJ22RDKI3/action/replication_record"}},"created_at":"2026-06-19T16:09:51.984132+00:00","updated_at":"2026-06-19T16:09:51.984132+00:00"}