{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZCAJIO3PRRJAWSGCS4AABISLRM","short_pith_number":"pith:ZCAJIO3P","schema_version":"1.0","canonical_sha256":"c880943b6f8c520b48c2970000a24b8b3b597d3a4bf429e04ea1873600b591a2","source":{"kind":"arxiv","id":"2408.08123","version":4},"attestation_state":"computed","paper":{"title":"Single-loop methods for bilevel parameter learning in inverse imaging","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Ensio Suonper\\\"a, Tuomo Valkonen","submitted_at":"2024-08-15T12:50:07Z","abstract_excerpt":"Bilevel optimisation is used in inverse imaging problems for hyperparameter learning/identification and experimental design, for instance, to find optimal regularisation parameters and forward operators. However, computationally, the process is costly. To reduce this cost, recently so-called single-loop approaches have been introduced. On each step of an outer optimisation method, they take just a single gradient step towards the solution of the inner problem. In this paper, we flexibilise the inner algorithm to include standard methods in inverse imaging. Moreover, as we have recently shown, "},"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":"2408.08123","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"math.OC","submitted_at":"2024-08-15T12:50:07Z","cross_cats_sorted":[],"title_canon_sha256":"7cbf450d1d54510edfd2420e32eaefd7417641f26aea77c9cb2cc7d1bd04dba9","abstract_canon_sha256":"e18d42f87aec351e943ced97c83e84649a13351fdad98870067da862c8a0daeb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:45.832813Z","signature_b64":"URsCeJ9LEZTEKhqwJnB0kraub10MvqI5Opd+D2pnJzmBa4wBY09VKHjCUtY/w1JDi5w5xVH4HwIfhybrviJAAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c880943b6f8c520b48c2970000a24b8b3b597d3a4bf429e04ea1873600b591a2","last_reissued_at":"2026-07-05T11:48:45.832399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:45.832399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Single-loop methods for bilevel parameter learning in inverse imaging","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Ensio Suonper\\\"a, Tuomo Valkonen","submitted_at":"2024-08-15T12:50:07Z","abstract_excerpt":"Bilevel optimisation is used in inverse imaging problems for hyperparameter learning/identification and experimental design, for instance, to find optimal regularisation parameters and forward operators. However, computationally, the process is costly. To reduce this cost, recently so-called single-loop approaches have been introduced. On each step of an outer optimisation method, they take just a single gradient step towards the solution of the inner problem. In this paper, we flexibilise the inner algorithm to include standard methods in inverse imaging. Moreover, as we have recently shown, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08123","kind":"arxiv","version":4},"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/2408.08123/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":"2408.08123","created_at":"2026-07-05T11:48:45.832455+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.08123v4","created_at":"2026-07-05T11:48:45.832455+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08123","created_at":"2026-07-05T11:48:45.832455+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZCAJIO3PRRJA","created_at":"2026-07-05T11:48:45.832455+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZCAJIO3PRRJAWSGC","created_at":"2026-07-05T11:48:45.832455+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZCAJIO3P","created_at":"2026-07-05T11:48:45.832455+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10951","citing_title":"Dynamic inverse problems: Single-loop online algorithms","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZCAJIO3PRRJAWSGCS4AABISLRM","json":"https://pith.science/pith/ZCAJIO3PRRJAWSGCS4AABISLRM.json","graph_json":"https://pith.science/api/pith-number/ZCAJIO3PRRJAWSGCS4AABISLRM/graph.json","events_json":"https://pith.science/api/pith-number/ZCAJIO3PRRJAWSGCS4AABISLRM/events.json","paper":"https://pith.science/paper/ZCAJIO3P"},"agent_actions":{"view_html":"https://pith.science/pith/ZCAJIO3PRRJAWSGCS4AABISLRM","download_json":"https://pith.science/pith/ZCAJIO3PRRJAWSGCS4AABISLRM.json","view_paper":"https://pith.science/paper/ZCAJIO3P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.08123&json=true","fetch_graph":"https://pith.science/api/pith-number/ZCAJIO3PRRJAWSGCS4AABISLRM/graph.json","fetch_events":"https://pith.science/api/pith-number/ZCAJIO3PRRJAWSGCS4AABISLRM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZCAJIO3PRRJAWSGCS4AABISLRM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZCAJIO3PRRJAWSGCS4AABISLRM/action/storage_attestation","attest_author":"https://pith.science/pith/ZCAJIO3PRRJAWSGCS4AABISLRM/action/author_attestation","sign_citation":"https://pith.science/pith/ZCAJIO3PRRJAWSGCS4AABISLRM/action/citation_signature","submit_replication":"https://pith.science/pith/ZCAJIO3PRRJAWSGCS4AABISLRM/action/replication_record"}},"created_at":"2026-07-05T11:48:45.832455+00:00","updated_at":"2026-07-05T11:48:45.832455+00:00"}