{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PGYZD4FMHKMEYC2O2TP5UHPGS6","short_pith_number":"pith:PGYZD4FM","schema_version":"1.0","canonical_sha256":"79b191f0ac3a984c0b4ed4dfda1de697b14d1e0d3388e2167b23e7719f0f5c57","source":{"kind":"arxiv","id":"2212.08260","version":1},"attestation_state":"computed","paper":{"title":"End-to-End Learning to Warm-Start for Real-Time Quadratic Optimization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Bartolomeo Stellato, Brandon Amos, Georgina Hall, Rajiv Sambharya","submitted_at":"2022-12-16T03:12:39Z","abstract_excerpt":"First-order methods are widely used to solve convex quadratic programs (QPs) in real-time applications because of their low per-iteration cost. However, they can suffer from slow convergence to accurate solutions. In this paper, we present a framework which learns an effective warm-start for a popular first-order method in real-time applications, Douglas-Rachford (DR) splitting, across a family of parametric QPs. This framework consists of two modules: a feedforward neural network block, which takes as input the parameters of the QP and outputs a warm-start, and a block which performs a fixed "},"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":"2212.08260","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"math.OC","submitted_at":"2022-12-16T03:12:39Z","cross_cats_sorted":[],"title_canon_sha256":"4aabc4caefb86b37652105164133144d569e84137918ef9798e990d650e24d7c","abstract_canon_sha256":"10d30da78ab58dcb7521e36830b30c9e92e828b6f2c49ebe221a427b4d84badb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:54.598171Z","signature_b64":"gim5G2hbziiJ5fxj9K2IQ+0dSeBglWEnskDcr+SQSB1tpOlm9KvTpAlhIfvlMe2X62jC6RC8lsSUP8CJ58yiAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79b191f0ac3a984c0b4ed4dfda1de697b14d1e0d3388e2167b23e7719f0f5c57","last_reissued_at":"2026-07-05T05:25:54.597677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:54.597677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Learning to Warm-Start for Real-Time Quadratic Optimization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Bartolomeo Stellato, Brandon Amos, Georgina Hall, Rajiv Sambharya","submitted_at":"2022-12-16T03:12:39Z","abstract_excerpt":"First-order methods are widely used to solve convex quadratic programs (QPs) in real-time applications because of their low per-iteration cost. However, they can suffer from slow convergence to accurate solutions. In this paper, we present a framework which learns an effective warm-start for a popular first-order method in real-time applications, Douglas-Rachford (DR) splitting, across a family of parametric QPs. This framework consists of two modules: a feedforward neural network block, which takes as input the parameters of the QP and outputs a warm-start, and a block which performs a fixed "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08260","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/2212.08260/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":"2212.08260","created_at":"2026-07-05T05:25:54.597738+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.08260v1","created_at":"2026-07-05T05:25:54.597738+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08260","created_at":"2026-07-05T05:25:54.597738+00:00"},{"alias_kind":"pith_short_12","alias_value":"PGYZD4FMHKME","created_at":"2026-07-05T05:25:54.597738+00:00"},{"alias_kind":"pith_short_16","alias_value":"PGYZD4FMHKMEYC2O","created_at":"2026-07-05T05:25:54.597738+00:00"},{"alias_kind":"pith_short_8","alias_value":"PGYZD4FM","created_at":"2026-07-05T05:25:54.597738+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19328","citing_title":"UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based Reinforcement Learning","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PGYZD4FMHKMEYC2O2TP5UHPGS6","json":"https://pith.science/pith/PGYZD4FMHKMEYC2O2TP5UHPGS6.json","graph_json":"https://pith.science/api/pith-number/PGYZD4FMHKMEYC2O2TP5UHPGS6/graph.json","events_json":"https://pith.science/api/pith-number/PGYZD4FMHKMEYC2O2TP5UHPGS6/events.json","paper":"https://pith.science/paper/PGYZD4FM"},"agent_actions":{"view_html":"https://pith.science/pith/PGYZD4FMHKMEYC2O2TP5UHPGS6","download_json":"https://pith.science/pith/PGYZD4FMHKMEYC2O2TP5UHPGS6.json","view_paper":"https://pith.science/paper/PGYZD4FM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.08260&json=true","fetch_graph":"https://pith.science/api/pith-number/PGYZD4FMHKMEYC2O2TP5UHPGS6/graph.json","fetch_events":"https://pith.science/api/pith-number/PGYZD4FMHKMEYC2O2TP5UHPGS6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PGYZD4FMHKMEYC2O2TP5UHPGS6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PGYZD4FMHKMEYC2O2TP5UHPGS6/action/storage_attestation","attest_author":"https://pith.science/pith/PGYZD4FMHKMEYC2O2TP5UHPGS6/action/author_attestation","sign_citation":"https://pith.science/pith/PGYZD4FMHKMEYC2O2TP5UHPGS6/action/citation_signature","submit_replication":"https://pith.science/pith/PGYZD4FMHKMEYC2O2TP5UHPGS6/action/replication_record"}},"created_at":"2026-07-05T05:25:54.597738+00:00","updated_at":"2026-07-05T05:25:54.597738+00:00"}