{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IT7VOFTWYRH66D2B32F22TKEV5","short_pith_number":"pith:IT7VOFTW","schema_version":"1.0","canonical_sha256":"44ff571676c44fef0f41de8bad4d44af7d495e749eb9b2ac6d55641f405de744","source":{"kind":"arxiv","id":"2402.15646","version":2},"attestation_state":"computed","paper":{"title":"Stochastic ISTA/FISTA Adaptive Step Search Algorithms for Convex Composite Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Katya Scheinberg, Lam M. Nguyen, Trang H. Tran","submitted_at":"2024-02-23T23:07:59Z","abstract_excerpt":"We develop and analyze stochastic variants of ISTA and a full backtracking FISTA algorithms [Beck and Teboulle, 2009, Scheinberg et al., 2014] for composite optimization without the assumption that stochastic gradient is an unbiased estimator. This work extends analysis of inexact fixed step ISTA/FISTA in [Schmidt et al., 2011] to the case of stochastic gradient estimates and adaptive step-size parameter chosen by backtracking. It also extends the framework for analyzing stochastic line-search method in [Cartis and Scheinberg, 2018] to the proximal gradient framework as well as to the accelera"},"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":"2402.15646","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-02-23T23:07:59Z","cross_cats_sorted":[],"title_canon_sha256":"6d7ab14214d8cee0381ea08e4c06ce39aab5b4c982762b2911dc6b9649985f0a","abstract_canon_sha256":"37f12b93f335af2b149773e32857ec6737cd890ce16a3f013a923efc2835d903"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:38.902633Z","signature_b64":"gcaq1ESDDkEiJ/1R+1+gyJsi5vzemN4xFsGKs2+VpWjMU1bm6bnHNxwmlYO3Mwt0pZbNKka7XZOAb9G2GANDAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44ff571676c44fef0f41de8bad4d44af7d495e749eb9b2ac6d55641f405de744","last_reissued_at":"2026-07-05T10:13:38.902118Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:38.902118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic ISTA/FISTA Adaptive Step Search Algorithms for Convex Composite Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Katya Scheinberg, Lam M. Nguyen, Trang H. Tran","submitted_at":"2024-02-23T23:07:59Z","abstract_excerpt":"We develop and analyze stochastic variants of ISTA and a full backtracking FISTA algorithms [Beck and Teboulle, 2009, Scheinberg et al., 2014] for composite optimization without the assumption that stochastic gradient is an unbiased estimator. This work extends analysis of inexact fixed step ISTA/FISTA in [Schmidt et al., 2011] to the case of stochastic gradient estimates and adaptive step-size parameter chosen by backtracking. It also extends the framework for analyzing stochastic line-search method in [Cartis and Scheinberg, 2018] to the proximal gradient framework as well as to the accelera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15646","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/2402.15646/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":"2402.15646","created_at":"2026-07-05T10:13:38.902179+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.15646v2","created_at":"2026-07-05T10:13:38.902179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15646","created_at":"2026-07-05T10:13:38.902179+00:00"},{"alias_kind":"pith_short_12","alias_value":"IT7VOFTWYRH6","created_at":"2026-07-05T10:13:38.902179+00:00"},{"alias_kind":"pith_short_16","alias_value":"IT7VOFTWYRH66D2B","created_at":"2026-07-05T10:13:38.902179+00:00"},{"alias_kind":"pith_short_8","alias_value":"IT7VOFTW","created_at":"2026-07-05T10:13:38.902179+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.15526","citing_title":"Robust Accelerated Adaptive Search: High-Probability Complexity Bounds under Bounded-Moment Stochastic Oracles","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IT7VOFTWYRH66D2B32F22TKEV5","json":"https://pith.science/pith/IT7VOFTWYRH66D2B32F22TKEV5.json","graph_json":"https://pith.science/api/pith-number/IT7VOFTWYRH66D2B32F22TKEV5/graph.json","events_json":"https://pith.science/api/pith-number/IT7VOFTWYRH66D2B32F22TKEV5/events.json","paper":"https://pith.science/paper/IT7VOFTW"},"agent_actions":{"view_html":"https://pith.science/pith/IT7VOFTWYRH66D2B32F22TKEV5","download_json":"https://pith.science/pith/IT7VOFTWYRH66D2B32F22TKEV5.json","view_paper":"https://pith.science/paper/IT7VOFTW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.15646&json=true","fetch_graph":"https://pith.science/api/pith-number/IT7VOFTWYRH66D2B32F22TKEV5/graph.json","fetch_events":"https://pith.science/api/pith-number/IT7VOFTWYRH66D2B32F22TKEV5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IT7VOFTWYRH66D2B32F22TKEV5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IT7VOFTWYRH66D2B32F22TKEV5/action/storage_attestation","attest_author":"https://pith.science/pith/IT7VOFTWYRH66D2B32F22TKEV5/action/author_attestation","sign_citation":"https://pith.science/pith/IT7VOFTWYRH66D2B32F22TKEV5/action/citation_signature","submit_replication":"https://pith.science/pith/IT7VOFTWYRH66D2B32F22TKEV5/action/replication_record"}},"created_at":"2026-07-05T10:13:38.902179+00:00","updated_at":"2026-07-05T10:13:38.902179+00:00"}