{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TNRIR4NGFU7KCF6Z4UX4MMLIQL","short_pith_number":"pith:TNRIR4NG","schema_version":"1.0","canonical_sha256":"9b6288f1a62d3ea117d9e52fc6316882d338eb1d384f398781b489a72ce6308e","source":{"kind":"arxiv","id":"2605.13144","version":1},"attestation_state":"computed","paper":{"title":"On a posteriori stopping rules of adaptive stochastic heavy ball method for ill-posed problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Adaptive stochastic heavy ball method with a posteriori stopping rule converges almost surely for ill-posed inverse problems.","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Qinian Jin, Ruixue Gu","submitted_at":"2026-05-13T08:10:14Z","abstract_excerpt":"In this paper we develop a stochastic heavy ball method for solving ill-posed inverse problems. The method updates the iterate using only a randomly selected equation at each iteration step while incorporating a momentum term into the process. To facilitate fast convergence, we propose an adaptive strategy for selecting the step size and the momentum coefficient. Inspired by the spirit of the discrepancy principle, we introduce an {\\it a posteriori} stopping rule for our adaptive stochastic heavy ball method. This rule avoids the need to compute residuals of all equations in the system at ever"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.13144","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2026-05-13T08:10:14Z","cross_cats_sorted":["cs.NA"],"title_canon_sha256":"21b488d6f4cf1e372c0c3eb1bd87ecd94453a071909426470a3b2a9851965d04","abstract_canon_sha256":"6b0c39c6491ae101048d52c0ea18a86d6f105ade235c0fd04358f19069993cb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:08:57.353879Z","signature_b64":"QjWK18FGpKGL6V0mpjQUZPVkp24TYGXcDHZvtsfrm7UaQN42a6nQQnpfzitpdIaH32sAdoQVBv1G521eKvNVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b6288f1a62d3ea117d9e52fc6316882d338eb1d384f398781b489a72ce6308e","last_reissued_at":"2026-05-18T03:08:57.353059Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:08:57.353059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On a posteriori stopping rules of adaptive stochastic heavy ball method for ill-posed problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Adaptive stochastic heavy ball method with a posteriori stopping rule converges almost surely for ill-posed inverse problems.","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Qinian Jin, Ruixue Gu","submitted_at":"2026-05-13T08:10:14Z","abstract_excerpt":"In this paper we develop a stochastic heavy ball method for solving ill-posed inverse problems. The method updates the iterate using only a randomly selected equation at each iteration step while incorporating a momentum term into the process. To facilitate fast convergence, we propose an adaptive strategy for selecting the step size and the momentum coefficient. Inspired by the spirit of the discrepancy principle, we introduce an {\\it a posteriori} stopping rule for our adaptive stochastic heavy ball method. This rule avoids the need to compute residuals of all equations in the system at ever"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Under suitable conditions, we establish almost sure convergence as well as convergence in expectation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The 'suitable conditions' on the problem, noise level, adaptive parameters, and penalty functions that are required for the convergence statements to hold.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"An adaptive stochastic heavy ball method with a discrepancy-based a posteriori stopping rule is introduced for ill-posed inverse problems, proving almost sure and expectation convergence while improving efficiency for large systems.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Adaptive stochastic heavy ball method with a posteriori stopping rule converges almost surely for ill-posed inverse problems.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"90e7c6ed84f8dfbf68dedc9c41cf47ba9ffec433c705b5a2eb359f02e5c2a35c"},"source":{"id":"2605.13144","kind":"arxiv","version":1},"verdict":{"id":"ab4a8443-d7c7-4a0d-8ca8-f605638707ca","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T18:37:19.350357Z","strongest_claim":"Under suitable conditions, we establish almost sure convergence as well as convergence in expectation.","one_line_summary":"An adaptive stochastic heavy ball method with a discrepancy-based a posteriori stopping rule is introduced for ill-posed inverse problems, proving almost sure and expectation convergence while improving efficiency for large systems.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The 'suitable conditions' on the problem, noise level, adaptive parameters, and penalty functions that are required for the convergence statements to hold.","pith_extraction_headline":"Adaptive stochastic heavy ball method with a posteriori stopping rule converges almost surely for ill-posed inverse problems."},"references":{"count":30,"sample":[{"doi":"","year":2007,"title":"R. N. Bhattacharya and E. C. W aymire. A basic course in probability theory . New York: Springer, 2007","work_id":"ee1171b8-4ecc-4f99-a677-b55dec04956a","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2011,"title":"R. I. Bot ¸ and T. Hein. Iterative regularization with a general penalty term-theo ry and application to L1 and TV regularization . Inverse Problems, 28 (2011), 104010","work_id":"b40079de-f242-4391-9450-8f30ab565d07","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2010,"title":"L. Bottou. Large-scale machine learning with stochastic gradient des cent. Proceedings of COMPSTAT2010 (Berlin: Springer), 2010, pp. 177-186","work_id":"0dc5082f-fb90-4810-83a6-d20397a540ff","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"L. Bottou, F. E. Curtis and J. Nocedal. Optimization methods for large-scale machine learning. SIAM Review, 60 (2018), pp. 223-311","work_id":"4450a068-8e14-4c9c-9499-82da5a668dd7","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1990,"title":"I. Cioranescu. Geometry of Banach spaces, duality mappings and nonlinear p roblems. Kluwer Academic Pub, 1990","work_id":"483370d4-eda3-41af-991c-b22b8c075052","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":30,"snapshot_sha256":"99f80c624f400987aa62d77002beeb425c279f6be4af8ece399c1e2fc311d384","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":"2605.13144","created_at":"2026-05-18T03:08:57.353183+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13144v1","created_at":"2026-05-18T03:08:57.353183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13144","created_at":"2026-05-18T03:08:57.353183+00:00"},{"alias_kind":"pith_short_12","alias_value":"TNRIR4NGFU7K","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"TNRIR4NGFU7KCF6Z","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"TNRIR4NG","created_at":"2026-05-18T12:33:37.589309+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/TNRIR4NGFU7KCF6Z4UX4MMLIQL","json":"https://pith.science/pith/TNRIR4NGFU7KCF6Z4UX4MMLIQL.json","graph_json":"https://pith.science/api/pith-number/TNRIR4NGFU7KCF6Z4UX4MMLIQL/graph.json","events_json":"https://pith.science/api/pith-number/TNRIR4NGFU7KCF6Z4UX4MMLIQL/events.json","paper":"https://pith.science/paper/TNRIR4NG"},"agent_actions":{"view_html":"https://pith.science/pith/TNRIR4NGFU7KCF6Z4UX4MMLIQL","download_json":"https://pith.science/pith/TNRIR4NGFU7KCF6Z4UX4MMLIQL.json","view_paper":"https://pith.science/paper/TNRIR4NG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13144&json=true","fetch_graph":"https://pith.science/api/pith-number/TNRIR4NGFU7KCF6Z4UX4MMLIQL/graph.json","fetch_events":"https://pith.science/api/pith-number/TNRIR4NGFU7KCF6Z4UX4MMLIQL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TNRIR4NGFU7KCF6Z4UX4MMLIQL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TNRIR4NGFU7KCF6Z4UX4MMLIQL/action/storage_attestation","attest_author":"https://pith.science/pith/TNRIR4NGFU7KCF6Z4UX4MMLIQL/action/author_attestation","sign_citation":"https://pith.science/pith/TNRIR4NGFU7KCF6Z4UX4MMLIQL/action/citation_signature","submit_replication":"https://pith.science/pith/TNRIR4NGFU7KCF6Z4UX4MMLIQL/action/replication_record"}},"created_at":"2026-05-18T03:08:57.353183+00:00","updated_at":"2026-05-18T03:08:57.353183+00:00"}