{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4C6MIC647NGIGXQZFPGJ36HF3H","short_pith_number":"pith:4C6MIC64","schema_version":"1.0","canonical_sha256":"e0bcc40bdcfb4c835e192bcc9df8e5d9fcbf3c9da704d5a345ad13b608123290","source":{"kind":"arxiv","id":"2407.21221","version":2},"attestation_state":"computed","paper":{"title":"Dynamic FISTA for Convex Composite Bi-Level Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Marc Teboulle, Roey Merchav, Shoham Sabach","submitted_at":"2024-07-30T22:21:33Z","abstract_excerpt":"In this paper, we study convex bi-level optimization problems where both the inner and outer levels are given as a composite convex minimization. We propose the Fast Bi-level Proximal Gradient (FBi-PG) algorithm, which can be interpreted as applying FISTA to a dynamic regularized composite objective function. The dynamic nature of the regularization parameters allows to achieve an optimal fast convergence rate of $O(1/k^{2})$ in terms of the inner objective function. This is the fastest known convergence rate under no additional restrictive assumptions. We also show that FBi-PG achieves sub-li"},"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":"2407.21221","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-07-30T22:21:33Z","cross_cats_sorted":[],"title_canon_sha256":"58da0ebea497ef134c2629abdb780e0c7f889e768985114b72ce082a462178b4","abstract_canon_sha256":"6156f0ea53605ed4f04a52050a64f92e0e093595e6c35b4e56a7fd79a444753e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:04.265423Z","signature_b64":"wIrbrcq6RPaBPUA7FBzAOlJ3H1X7RQQXQ8OQAJauz2lOZDzUQGqTwhRhXdICQJ8mwphuboss9lD5MWtyZljDBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0bcc40bdcfb4c835e192bcc9df8e5d9fcbf3c9da704d5a345ad13b608123290","last_reissued_at":"2026-07-05T11:20:04.264965Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:04.264965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic FISTA for Convex Composite Bi-Level Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Marc Teboulle, Roey Merchav, Shoham Sabach","submitted_at":"2024-07-30T22:21:33Z","abstract_excerpt":"In this paper, we study convex bi-level optimization problems where both the inner and outer levels are given as a composite convex minimization. We propose the Fast Bi-level Proximal Gradient (FBi-PG) algorithm, which can be interpreted as applying FISTA to a dynamic regularized composite objective function. The dynamic nature of the regularization parameters allows to achieve an optimal fast convergence rate of $O(1/k^{2})$ in terms of the inner objective function. This is the fastest known convergence rate under no additional restrictive assumptions. We also show that FBi-PG achieves sub-li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21221","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/2407.21221/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":"2407.21221","created_at":"2026-07-05T11:20:04.265022+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.21221v2","created_at":"2026-07-05T11:20:04.265022+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21221","created_at":"2026-07-05T11:20:04.265022+00:00"},{"alias_kind":"pith_short_12","alias_value":"4C6MIC647NGI","created_at":"2026-07-05T11:20:04.265022+00:00"},{"alias_kind":"pith_short_16","alias_value":"4C6MIC647NGIGXQZ","created_at":"2026-07-05T11:20:04.265022+00:00"},{"alias_kind":"pith_short_8","alias_value":"4C6MIC64","created_at":"2026-07-05T11:20:04.265022+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.14389","citing_title":"Accelerating Diagonal Methods for Bilevel Optimization: Unified Convergence via Continuous-Time Dynamics","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4C6MIC647NGIGXQZFPGJ36HF3H","json":"https://pith.science/pith/4C6MIC647NGIGXQZFPGJ36HF3H.json","graph_json":"https://pith.science/api/pith-number/4C6MIC647NGIGXQZFPGJ36HF3H/graph.json","events_json":"https://pith.science/api/pith-number/4C6MIC647NGIGXQZFPGJ36HF3H/events.json","paper":"https://pith.science/paper/4C6MIC64"},"agent_actions":{"view_html":"https://pith.science/pith/4C6MIC647NGIGXQZFPGJ36HF3H","download_json":"https://pith.science/pith/4C6MIC647NGIGXQZFPGJ36HF3H.json","view_paper":"https://pith.science/paper/4C6MIC64","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.21221&json=true","fetch_graph":"https://pith.science/api/pith-number/4C6MIC647NGIGXQZFPGJ36HF3H/graph.json","fetch_events":"https://pith.science/api/pith-number/4C6MIC647NGIGXQZFPGJ36HF3H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4C6MIC647NGIGXQZFPGJ36HF3H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4C6MIC647NGIGXQZFPGJ36HF3H/action/storage_attestation","attest_author":"https://pith.science/pith/4C6MIC647NGIGXQZFPGJ36HF3H/action/author_attestation","sign_citation":"https://pith.science/pith/4C6MIC647NGIGXQZFPGJ36HF3H/action/citation_signature","submit_replication":"https://pith.science/pith/4C6MIC647NGIGXQZFPGJ36HF3H/action/replication_record"}},"created_at":"2026-07-05T11:20:04.265022+00:00","updated_at":"2026-07-05T11:20:04.265022+00:00"}