{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BVACLJH6GKTCIBCA6DJ22RDKI3","short_pith_number":"pith:BVACLJH6","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"},"canonical_sha256":"0d4025a4fe32a6240440f0d3ad446a46e5f4c9795bad2d393266281c8f353392","source":{"kind":"arxiv","id":"2510.27211","version":7},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.27211","created_at":"2026-06-19T16:09:51Z"},{"alias_kind":"arxiv_version","alias_value":"2510.27211v7","created_at":"2026-06-19T16:09:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.27211","created_at":"2026-06-19T16:09:51Z"},{"alias_kind":"pith_short_12","alias_value":"BVACLJH6GKTC","created_at":"2026-06-19T16:09:51Z"},{"alias_kind":"pith_short_16","alias_value":"BVACLJH6GKTCIBCA","created_at":"2026-06-19T16:09:51Z"},{"alias_kind":"pith_short_8","alias_value":"BVACLJH6","created_at":"2026-06-19T16:09:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BVACLJH6GKTCIBCA6DJ22RDKI3","target":"record","payload":{"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"},"canonical_sha256":"0d4025a4fe32a6240440f0d3ad446a46e5f4c9795bad2d393266281c8f353392","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"},"source_kind":"arxiv","source_id":"2510.27211","source_version":7,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:09:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uGsgKlEq4ldSd0FD/l8PfsGI5EqenFTs7vkCmrMxprhLEN9IVtmgVkn9Pch76yacVtwtVziYT+nYcfH6mJM4CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-23T13:18:48.843217Z"},"content_sha256":"5a423666ef0ea2bc1821cc3840c2ac645700a8198f5aae421fefa45abb7c5f4a","schema_version":"1.0","event_id":"sha256:5a423666ef0ea2bc1821cc3840c2ac645700a8198f5aae421fefa45abb7c5f4a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BVACLJH6GKTCIBCA6DJ22RDKI3","target":"graph","payload":{"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"},"verdict_id":"88d7ccfa-6a77-443f-a86b-389c918d8860"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:09:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N1g4f/JBhr5ZYGfrD9dzQjXV1OcDJ1nXquyr0aF7uW871KvXKEZhPGzkAbiD096DFsWsBb0hAjM3RmkrVNY+BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-23T13:18:48.843719Z"},"content_sha256":"8395e95a83e3e76e072bfe7751443417245a0c6593b4bdb8f4a06a1016b0202e","schema_version":"1.0","event_id":"sha256:8395e95a83e3e76e072bfe7751443417245a0c6593b4bdb8f4a06a1016b0202e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BVACLJH6GKTCIBCA6DJ22RDKI3/bundle.json","state_url":"https://pith.science/pith/BVACLJH6GKTCIBCA6DJ22RDKI3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BVACLJH6GKTCIBCA6DJ22RDKI3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-23T13:18:48Z","links":{"resolver":"https://pith.science/pith/BVACLJH6GKTCIBCA6DJ22RDKI3","bundle":"https://pith.science/pith/BVACLJH6GKTCIBCA6DJ22RDKI3/bundle.json","state":"https://pith.science/pith/BVACLJH6GKTCIBCA6DJ22RDKI3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BVACLJH6GKTCIBCA6DJ22RDKI3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BVACLJH6GKTCIBCA6DJ22RDKI3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b7b329f9f7f8d23b6251197e581f62e929e7d70b5260fa9025da878b1b62b810","cross_cats_sorted":["eess.SP","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-10-31T06:12:49Z","title_canon_sha256":"d41493dca1126beb10d36d1916e60112686faac6c33662d523c88ee9443cb719"},"schema_version":"1.0","source":{"id":"2510.27211","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.27211","created_at":"2026-06-19T16:09:51Z"},{"alias_kind":"arxiv_version","alias_value":"2510.27211v7","created_at":"2026-06-19T16:09:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.27211","created_at":"2026-06-19T16:09:51Z"},{"alias_kind":"pith_short_12","alias_value":"BVACLJH6GKTC","created_at":"2026-06-19T16:09:51Z"},{"alias_kind":"pith_short_16","alias_value":"BVACLJH6GKTCIBCA","created_at":"2026-06-19T16:09:51Z"},{"alias_kind":"pith_short_8","alias_value":"BVACLJH6","created_at":"2026-06-19T16:09:51Z"}],"graph_snapshots":[{"event_id":"sha256:8395e95a83e3e76e072bfe7751443417245a0c6593b4bdb8f4a06a1016b0202e","target":"graph","created_at":"2026-06-19T16:09:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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)."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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"}],"snapshot_sha256":"954b757783bb55ac136cca34254f8fe324fc9626448e07548e837d984c17e2a1"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"06041956e969190d6742826d1ed79fa4dd6dd408be486674d710b036b3b67cbd"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2510.27211/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Henry Pritchard, Rahul Parhi","cross_cats":["eess.SP","stat.ML"],"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","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-10-31T06:12:49Z","title":"Nonasymptotic Convergence Rates for Plug-and-Play Methods With MMSE Denoisers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.27211","kind":"arxiv","version":7},"verdict":{"created_at":"2026-05-18T03:34:56.233495Z","id":"88d7ccfa-6a77-443f-a86b-389c918d8860","model_set":{"reader":"grok-4.3"},"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","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","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.","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)."}},"verdict_id":"88d7ccfa-6a77-443f-a86b-389c918d8860"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5a423666ef0ea2bc1821cc3840c2ac645700a8198f5aae421fefa45abb7c5f4a","target":"record","created_at":"2026-06-19T16:09:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b7b329f9f7f8d23b6251197e581f62e929e7d70b5260fa9025da878b1b62b810","cross_cats_sorted":["eess.SP","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-10-31T06:12:49Z","title_canon_sha256":"d41493dca1126beb10d36d1916e60112686faac6c33662d523c88ee9443cb719"},"schema_version":"1.0","source":{"id":"2510.27211","kind":"arxiv","version":7}},"canonical_sha256":"0d4025a4fe32a6240440f0d3ad446a46e5f4c9795bad2d393266281c8f353392","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d4025a4fe32a6240440f0d3ad446a46e5f4c9795bad2d393266281c8f353392","first_computed_at":"2026-06-19T16:09:51.984059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:09:51.984059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZIgo5yxmtXC/ZpExwZ9SglQ07MJ6uvrAQq9ad677eJPhy9Tc7BpzEsGEErS0w/y1nFjotRBzj+ZFOlcXwCkNDQ==","signature_status":"signed_v1","signed_at":"2026-06-19T16:09:51.984646Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.27211","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a423666ef0ea2bc1821cc3840c2ac645700a8198f5aae421fefa45abb7c5f4a","sha256:8395e95a83e3e76e072bfe7751443417245a0c6593b4bdb8f4a06a1016b0202e"],"state_sha256":"6581684e0e803594a159aa9fe10eb25c67397815f1fdb84e342540cbe8623de6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mTpjduTXFqI+zT5aoUFwoNhXo92/m9NJ3092593nSghYWc1WKv6iiVQ58uEg4c+dAManwsSwCbxIfw/VYBJ2DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-23T13:18:48.846091Z","bundle_sha256":"5c5cfda2f6ccb3a231ee942c957aeb02f103a9063a5d716fcd4529630de1a545"}}