{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RRJ7USGZ5POQT6K64WY5APZMBO","short_pith_number":"pith:RRJ7USGZ","schema_version":"1.0","canonical_sha256":"8c53fa48d9ebdd09f95ee5b1d03f2c0b87325b9e2e691aac9a5734ed18fe83ab","source":{"kind":"arxiv","id":"2411.15717","version":1},"attestation_state":"computed","paper":{"title":"Learning Algorithm Hyperparameters for Fast Parametric Convex Optimization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Bartolomeo Stellato, Rajiv Sambharya","submitted_at":"2024-11-24T04:58:36Z","abstract_excerpt":"We introduce a machine-learning framework to learn the hyperparameter sequence of first-order methods (e.g., the step sizes in gradient descent) to quickly solve parametric convex optimization problems. Our computational architecture amounts to running fixed-point iterations where the hyperparameters are the same across all parametric instances and consists of two phases. In the first step-varying phase the hyperparameters vary across iterations, while in the second steady-state phase the hyperparameters are constant across iterations. Our learned optimizer is flexible in that it can be evalua"},"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":"2411.15717","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"math.OC","submitted_at":"2024-11-24T04:58:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"01a8f6b2c7a7f380f6f23eb1cdf7babdbfbd6ca96fd871388265c87c341d2054","abstract_canon_sha256":"f9758c5b373481166f1bd441ed1c1c80c6df4ed594e0fddee6b0adac8fd8d2b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:18.350263Z","signature_b64":"OKMqj5oO7d8ql3zPfTo4CQL9Ef4t6WX4RAsVwi0JGyhtRLS/ZimBkX8AcmHUmHnM7nWIzfghSvf24EBDpxPbCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c53fa48d9ebdd09f95ee5b1d03f2c0b87325b9e2e691aac9a5734ed18fe83ab","last_reissued_at":"2026-07-05T09:52:18.349768Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:18.349768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Algorithm Hyperparameters for Fast Parametric Convex Optimization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Bartolomeo Stellato, Rajiv Sambharya","submitted_at":"2024-11-24T04:58:36Z","abstract_excerpt":"We introduce a machine-learning framework to learn the hyperparameter sequence of first-order methods (e.g., the step sizes in gradient descent) to quickly solve parametric convex optimization problems. Our computational architecture amounts to running fixed-point iterations where the hyperparameters are the same across all parametric instances and consists of two phases. In the first step-varying phase the hyperparameters vary across iterations, while in the second steady-state phase the hyperparameters are constant across iterations. Our learned optimizer is flexible in that it can be evalua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15717","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/2411.15717/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":"2411.15717","created_at":"2026-07-05T09:52:18.349829+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15717v1","created_at":"2026-07-05T09:52:18.349829+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15717","created_at":"2026-07-05T09:52:18.349829+00:00"},{"alias_kind":"pith_short_12","alias_value":"RRJ7USGZ5POQ","created_at":"2026-07-05T09:52:18.349829+00:00"},{"alias_kind":"pith_short_16","alias_value":"RRJ7USGZ5POQT6K6","created_at":"2026-07-05T09:52:18.349829+00:00"},{"alias_kind":"pith_short_8","alias_value":"RRJ7USGZ","created_at":"2026-07-05T09:52:18.349829+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08735","citing_title":"Learning Adaptive Solvers for Distributed Factor Graph Optimization on Matrix Lie Groups","ref_index":186,"is_internal_anchor":true},{"citing_arxiv_id":"2606.19920","citing_title":"Deep-Unfolded Coordination","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2509.05288","citing_title":"Learning to accelerate distributed ADMM using graph neural networks","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26932","citing_title":"Learning Over-Relaxation Policies for ADMM with Convergence Guarantees","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RRJ7USGZ5POQT6K64WY5APZMBO","json":"https://pith.science/pith/RRJ7USGZ5POQT6K64WY5APZMBO.json","graph_json":"https://pith.science/api/pith-number/RRJ7USGZ5POQT6K64WY5APZMBO/graph.json","events_json":"https://pith.science/api/pith-number/RRJ7USGZ5POQT6K64WY5APZMBO/events.json","paper":"https://pith.science/paper/RRJ7USGZ"},"agent_actions":{"view_html":"https://pith.science/pith/RRJ7USGZ5POQT6K64WY5APZMBO","download_json":"https://pith.science/pith/RRJ7USGZ5POQT6K64WY5APZMBO.json","view_paper":"https://pith.science/paper/RRJ7USGZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15717&json=true","fetch_graph":"https://pith.science/api/pith-number/RRJ7USGZ5POQT6K64WY5APZMBO/graph.json","fetch_events":"https://pith.science/api/pith-number/RRJ7USGZ5POQT6K64WY5APZMBO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RRJ7USGZ5POQT6K64WY5APZMBO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RRJ7USGZ5POQT6K64WY5APZMBO/action/storage_attestation","attest_author":"https://pith.science/pith/RRJ7USGZ5POQT6K64WY5APZMBO/action/author_attestation","sign_citation":"https://pith.science/pith/RRJ7USGZ5POQT6K64WY5APZMBO/action/citation_signature","submit_replication":"https://pith.science/pith/RRJ7USGZ5POQT6K64WY5APZMBO/action/replication_record"}},"created_at":"2026-07-05T09:52:18.349829+00:00","updated_at":"2026-07-05T09:52:18.349829+00:00"}