{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3WSKYETSV6U2DXEE2YWST3ZGGX","short_pith_number":"pith:3WSKYETS","schema_version":"1.0","canonical_sha256":"dda4ac1272afa9a1dc84d62d29ef2635da1154704e957a9bfd3df8b6ceb512e8","source":{"kind":"arxiv","id":"2105.05210","version":1},"attestation_state":"computed","paper":{"title":"Accelerated Forward-Backward Optimization using Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Jevgenija Rudzusika, Jonas Adler, Ozan \\\"Oktem, Sebastian Banert","submitted_at":"2021-05-11T17:23:46Z","abstract_excerpt":"We propose several deep-learning accelerated optimization solvers with convergence guarantees. We use ideas from the analysis of accelerated forward-backward schemes like FISTA, but instead of the classical approach of proving convergence for a choice of parameters, such as a step-size, we show convergence whenever the update is chosen in a specific set. Rather than picking a point in this set using some predefined method, we train a deep neural network to pick the best update. Finally, we show that the method is applicable to several cases of smooth and non-smooth optimization and show superi"},"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":"2105.05210","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-05-11T17:23:46Z","cross_cats_sorted":[],"title_canon_sha256":"80aec3f9f5985c46068aced71f628cc5b3a596f4c8c7454d0ed3b69e4c64ae49","abstract_canon_sha256":"1f73778937da9551527980341784bcab69651cf86642c9be7f5fe76be78e841f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:39:29.578294Z","signature_b64":"N7pYzHYN0hq+2ZyYeozIiMBgdEk4zNcPegr5/+l66RddZ3lOeIR4I3oH4PpsIWUCEIVL2B4zESxg2J2N6I5SDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dda4ac1272afa9a1dc84d62d29ef2635da1154704e957a9bfd3df8b6ceb512e8","last_reissued_at":"2026-07-05T02:39:29.577868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:39:29.577868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerated Forward-Backward Optimization using Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Jevgenija Rudzusika, Jonas Adler, Ozan \\\"Oktem, Sebastian Banert","submitted_at":"2021-05-11T17:23:46Z","abstract_excerpt":"We propose several deep-learning accelerated optimization solvers with convergence guarantees. We use ideas from the analysis of accelerated forward-backward schemes like FISTA, but instead of the classical approach of proving convergence for a choice of parameters, such as a step-size, we show convergence whenever the update is chosen in a specific set. Rather than picking a point in this set using some predefined method, we train a deep neural network to pick the best update. Finally, we show that the method is applicable to several cases of smooth and non-smooth optimization and show superi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.05210","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/2105.05210/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":"2105.05210","created_at":"2026-07-05T02:39:29.577941+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.05210v1","created_at":"2026-07-05T02:39:29.577941+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.05210","created_at":"2026-07-05T02:39:29.577941+00:00"},{"alias_kind":"pith_short_12","alias_value":"3WSKYETSV6U2","created_at":"2026-07-05T02:39:29.577941+00:00"},{"alias_kind":"pith_short_16","alias_value":"3WSKYETSV6U2DXEE","created_at":"2026-07-05T02:39:29.577941+00:00"},{"alias_kind":"pith_short_8","alias_value":"3WSKYETS","created_at":"2026-07-05T02:39:29.577941+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.15717","citing_title":"Learning Algorithm Hyperparameters for Fast Parametric Convex Optimization","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3WSKYETSV6U2DXEE2YWST3ZGGX","json":"https://pith.science/pith/3WSKYETSV6U2DXEE2YWST3ZGGX.json","graph_json":"https://pith.science/api/pith-number/3WSKYETSV6U2DXEE2YWST3ZGGX/graph.json","events_json":"https://pith.science/api/pith-number/3WSKYETSV6U2DXEE2YWST3ZGGX/events.json","paper":"https://pith.science/paper/3WSKYETS"},"agent_actions":{"view_html":"https://pith.science/pith/3WSKYETSV6U2DXEE2YWST3ZGGX","download_json":"https://pith.science/pith/3WSKYETSV6U2DXEE2YWST3ZGGX.json","view_paper":"https://pith.science/paper/3WSKYETS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.05210&json=true","fetch_graph":"https://pith.science/api/pith-number/3WSKYETSV6U2DXEE2YWST3ZGGX/graph.json","fetch_events":"https://pith.science/api/pith-number/3WSKYETSV6U2DXEE2YWST3ZGGX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3WSKYETSV6U2DXEE2YWST3ZGGX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3WSKYETSV6U2DXEE2YWST3ZGGX/action/storage_attestation","attest_author":"https://pith.science/pith/3WSKYETSV6U2DXEE2YWST3ZGGX/action/author_attestation","sign_citation":"https://pith.science/pith/3WSKYETSV6U2DXEE2YWST3ZGGX/action/citation_signature","submit_replication":"https://pith.science/pith/3WSKYETSV6U2DXEE2YWST3ZGGX/action/replication_record"}},"created_at":"2026-07-05T02:39:29.577941+00:00","updated_at":"2026-07-05T02:39:29.577941+00:00"}