{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:U6PLUCGVJSEFWDH4V3SZEGYB3Y","short_pith_number":"pith:U6PLUCGV","schema_version":"1.0","canonical_sha256":"a79eba08d54c885b0cfcaee5921b01de26dbe97a0a1f587bbec9afd031e5c90e","source":{"kind":"arxiv","id":"1904.03537","version":2},"attestation_state":"computed","paper":{"title":"Convex-Concave Backtracking for Inertial Bregman Proximal Gradient Algorithms in Non-Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Mahesh Chandra Mukkamala, Peter Ochs, Shoham Sabach, Thomas Pock","submitted_at":"2019-04-06T21:59:02Z","abstract_excerpt":"Backtracking line-search is an old yet powerful strategy for finding a better step sizes to be used in proximal gradient algorithms. The main principle is to locally find a simple convex upper bound of the objective function, which in turn controls the step size that is used. In case of inertial proximal gradient algorithms, the situation becomes much more difficult and usually leads to very restrictive rules on the extrapolation parameter. In this paper, we show that the extrapolation parameter can be controlled by locally finding also a simple concave lower bound of the objective function. T"},"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":"1904.03537","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-04-06T21:59:02Z","cross_cats_sorted":["cs.CV","cs.LG","cs.NA","math.NA"],"title_canon_sha256":"e9653b88ded0cea645aaf19525f206232c666ab04d2dc2c0baba29ca9b7e5e31","abstract_canon_sha256":"9fbec3fc92eee12ee876f09c0dd3e1ef9a1514f65d6f226f8c6c51d7c88e2cf8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T20:14:23.526662Z","signature_b64":"zPJCJkLZFKg+wWyuhFEsYYsnF44EjRdwqFVJucjIs3y/Q3hZCCHfOudGB7lkmyz4StSV4rIxJ5+6pljAfNCzCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a79eba08d54c885b0cfcaee5921b01de26dbe97a0a1f587bbec9afd031e5c90e","last_reissued_at":"2026-06-04T20:14:23.526215Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T20:14:23.526215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convex-Concave Backtracking for Inertial Bregman Proximal Gradient Algorithms in Non-Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Mahesh Chandra Mukkamala, Peter Ochs, Shoham Sabach, Thomas Pock","submitted_at":"2019-04-06T21:59:02Z","abstract_excerpt":"Backtracking line-search is an old yet powerful strategy for finding a better step sizes to be used in proximal gradient algorithms. The main principle is to locally find a simple convex upper bound of the objective function, which in turn controls the step size that is used. In case of inertial proximal gradient algorithms, the situation becomes much more difficult and usually leads to very restrictive rules on the extrapolation parameter. In this paper, we show that the extrapolation parameter can be controlled by locally finding also a simple concave lower bound of the objective function. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03537","kind":"arxiv","version":2},"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/1904.03537/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":"1904.03537","created_at":"2026-06-04T20:14:23.526273+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.03537v2","created_at":"2026-06-04T20:14:23.526273+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03537","created_at":"2026-06-04T20:14:23.526273+00:00"},{"alias_kind":"pith_short_12","alias_value":"U6PLUCGVJSEF","created_at":"2026-06-04T20:14:23.526273+00:00"},{"alias_kind":"pith_short_16","alias_value":"U6PLUCGVJSEFWDH4","created_at":"2026-06-04T20:14:23.526273+00:00"},{"alias_kind":"pith_short_8","alias_value":"U6PLUCGV","created_at":"2026-06-04T20:14:23.526273+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/U6PLUCGVJSEFWDH4V3SZEGYB3Y","json":"https://pith.science/pith/U6PLUCGVJSEFWDH4V3SZEGYB3Y.json","graph_json":"https://pith.science/api/pith-number/U6PLUCGVJSEFWDH4V3SZEGYB3Y/graph.json","events_json":"https://pith.science/api/pith-number/U6PLUCGVJSEFWDH4V3SZEGYB3Y/events.json","paper":"https://pith.science/paper/U6PLUCGV"},"agent_actions":{"view_html":"https://pith.science/pith/U6PLUCGVJSEFWDH4V3SZEGYB3Y","download_json":"https://pith.science/pith/U6PLUCGVJSEFWDH4V3SZEGYB3Y.json","view_paper":"https://pith.science/paper/U6PLUCGV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.03537&json=true","fetch_graph":"https://pith.science/api/pith-number/U6PLUCGVJSEFWDH4V3SZEGYB3Y/graph.json","fetch_events":"https://pith.science/api/pith-number/U6PLUCGVJSEFWDH4V3SZEGYB3Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U6PLUCGVJSEFWDH4V3SZEGYB3Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U6PLUCGVJSEFWDH4V3SZEGYB3Y/action/storage_attestation","attest_author":"https://pith.science/pith/U6PLUCGVJSEFWDH4V3SZEGYB3Y/action/author_attestation","sign_citation":"https://pith.science/pith/U6PLUCGVJSEFWDH4V3SZEGYB3Y/action/citation_signature","submit_replication":"https://pith.science/pith/U6PLUCGVJSEFWDH4V3SZEGYB3Y/action/replication_record"}},"created_at":"2026-06-04T20:14:23.526273+00:00","updated_at":"2026-06-04T20:14:23.526273+00:00"}