{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Y5OLNMCN4YBYVSUIEZJZ3CEBL5","short_pith_number":"pith:Y5OLNMCN","schema_version":"1.0","canonical_sha256":"c75cb6b04de6038aca8826539d88815f56d4619c183ccd04e9b181638f045a6d","source":{"kind":"arxiv","id":"2506.20630","version":1},"attestation_state":"computed","paper":{"title":"First-order methods for stochastic and finite-sum convex optimization with deterministic constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Yifeng Xiao, Zhaosong Lu","submitted_at":"2025-06-25T17:26:02Z","abstract_excerpt":"In this paper, we study a class of stochastic and finite-sum convex optimization problems with deterministic constraints. Existing methods typically aim to find an $\\epsilon$-$expectedly\\ feasible\\ stochastic\\ optimal$ solution, in which the expected constraint violation and expected optimality gap are both within a prescribed tolerance $\\epsilon$. However, in many practical applications, constraints must be nearly satisfied with certainty, rendering such solutions potentially unsuitable due to the risk of substantial violations. To address this issue, we propose stochastic first-order methods"},"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":"2506.20630","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-06-25T17:26:02Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA"],"title_canon_sha256":"a5527e0b77747f642b5e911c397da13796e6fe1cdf85753ec839d9c787d8ab72","abstract_canon_sha256":"e584cce468c89c9da40d588d872a3857c2431b7cabe81300f8d5c101cf9a355e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:15.397979Z","signature_b64":"xtC9sFc6xlhrj2idZod73ZMMZdL5+13oMkr/8Jk+KuxAg2WqmG+sEZw+SNEfPfdpLfj+bKVz8xD5hIYDGfTNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c75cb6b04de6038aca8826539d88815f56d4619c183ccd04e9b181638f045a6d","last_reissued_at":"2026-07-05T11:27:15.397424Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:15.397424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"First-order methods for stochastic and finite-sum convex optimization with deterministic constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Yifeng Xiao, Zhaosong Lu","submitted_at":"2025-06-25T17:26:02Z","abstract_excerpt":"In this paper, we study a class of stochastic and finite-sum convex optimization problems with deterministic constraints. Existing methods typically aim to find an $\\epsilon$-$expectedly\\ feasible\\ stochastic\\ optimal$ solution, in which the expected constraint violation and expected optimality gap are both within a prescribed tolerance $\\epsilon$. However, in many practical applications, constraints must be nearly satisfied with certainty, rendering such solutions potentially unsuitable due to the risk of substantial violations. To address this issue, we propose stochastic first-order methods"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20630","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/2506.20630/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":"2506.20630","created_at":"2026-07-05T11:27:15.397492+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.20630v1","created_at":"2026-07-05T11:27:15.397492+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20630","created_at":"2026-07-05T11:27:15.397492+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y5OLNMCN4YBY","created_at":"2026-07-05T11:27:15.397492+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y5OLNMCN4YBYVSUI","created_at":"2026-07-05T11:27:15.397492+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y5OLNMCN","created_at":"2026-07-05T11:27:15.397492+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.15240","citing_title":"Exact Reformulation and Optimization for Direct Metric Optimization in Binary Imbalanced Classification","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y5OLNMCN4YBYVSUIEZJZ3CEBL5","json":"https://pith.science/pith/Y5OLNMCN4YBYVSUIEZJZ3CEBL5.json","graph_json":"https://pith.science/api/pith-number/Y5OLNMCN4YBYVSUIEZJZ3CEBL5/graph.json","events_json":"https://pith.science/api/pith-number/Y5OLNMCN4YBYVSUIEZJZ3CEBL5/events.json","paper":"https://pith.science/paper/Y5OLNMCN"},"agent_actions":{"view_html":"https://pith.science/pith/Y5OLNMCN4YBYVSUIEZJZ3CEBL5","download_json":"https://pith.science/pith/Y5OLNMCN4YBYVSUIEZJZ3CEBL5.json","view_paper":"https://pith.science/paper/Y5OLNMCN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.20630&json=true","fetch_graph":"https://pith.science/api/pith-number/Y5OLNMCN4YBYVSUIEZJZ3CEBL5/graph.json","fetch_events":"https://pith.science/api/pith-number/Y5OLNMCN4YBYVSUIEZJZ3CEBL5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y5OLNMCN4YBYVSUIEZJZ3CEBL5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y5OLNMCN4YBYVSUIEZJZ3CEBL5/action/storage_attestation","attest_author":"https://pith.science/pith/Y5OLNMCN4YBYVSUIEZJZ3CEBL5/action/author_attestation","sign_citation":"https://pith.science/pith/Y5OLNMCN4YBYVSUIEZJZ3CEBL5/action/citation_signature","submit_replication":"https://pith.science/pith/Y5OLNMCN4YBYVSUIEZJZ3CEBL5/action/replication_record"}},"created_at":"2026-07-05T11:27:15.397492+00:00","updated_at":"2026-07-05T11:27:15.397492+00:00"}