{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:ZDYPJWLIN3K3BJI2D4LE5C2JSL","short_pith_number":"pith:ZDYPJWLI","schema_version":"1.0","canonical_sha256":"c8f0f4d9686ed5b0a51a1f164e8b4992d318b7ec88595e5f4ae30da9223a2bd7","source":{"kind":"arxiv","id":"1602.05394","version":2},"attestation_state":"computed","paper":{"title":"Online optimization and regret guarantees for non-additive long-term constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Cedric Archambeau, Dominik Csiba, Jim Huang, Rodolphe Jenatton","submitted_at":"2016-02-17T12:57:08Z","abstract_excerpt":"We consider online optimization in the 1-lookahead setting, where the objective does not decompose additively over the rounds of the online game. The resulting formulation enables us to deal with non-stationary and/or long-term constraints , which arise, for example, in online display advertising problems. We propose an on-line primal-dual algorithm for which we obtain dynamic cumulative regret guarantees. They depend on the convexity and the smoothness of the non-additive penalty, as well as terms capturing the smoothness with which the residuals of the non-stationary and long-term constraint"},"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":"1602.05394","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-17T12:57:08Z","cross_cats_sorted":["cs.LG","math.OC","math.ST","stat.TH"],"title_canon_sha256":"5ae37f13279118fd9288cbf3cb92d0ce941d22b3296161afb61c8807d2ec1b35","abstract_canon_sha256":"b71f4a1e0898493aab818af73808a628e74b1c5aad61495e61117effe7623306"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:43.201419Z","signature_b64":"E+2Cjh5u9xafuN5GkFIGqEjAVAw5FK7a8vG1hsWK5o41f3hpLdT91Z6Ed4Qv8fJiILggNng9TB0BphTgNE8tAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8f0f4d9686ed5b0a51a1f164e8b4992d318b7ec88595e5f4ae30da9223a2bd7","last_reissued_at":"2026-05-18T01:12:43.201087Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:43.201087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online optimization and regret guarantees for non-additive long-term constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Cedric Archambeau, Dominik Csiba, Jim Huang, Rodolphe Jenatton","submitted_at":"2016-02-17T12:57:08Z","abstract_excerpt":"We consider online optimization in the 1-lookahead setting, where the objective does not decompose additively over the rounds of the online game. The resulting formulation enables us to deal with non-stationary and/or long-term constraints , which arise, for example, in online display advertising problems. We propose an on-line primal-dual algorithm for which we obtain dynamic cumulative regret guarantees. They depend on the convexity and the smoothness of the non-additive penalty, as well as terms capturing the smoothness with which the residuals of the non-stationary and long-term constraint"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.05394","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":""},"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":"1602.05394","created_at":"2026-05-18T01:12:43.201139+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.05394v2","created_at":"2026-05-18T01:12:43.201139+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.05394","created_at":"2026-05-18T01:12:43.201139+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZDYPJWLIN3K3","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZDYPJWLIN3K3BJI2","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZDYPJWLI","created_at":"2026-05-18T12:30:53.716459+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2512.03915","citing_title":"A Theoretical Framework for Auxiliary-Loss-Free Load Balancing of Sparse Mixture-of-Experts in Large-Scale AI Models","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZDYPJWLIN3K3BJI2D4LE5C2JSL","json":"https://pith.science/pith/ZDYPJWLIN3K3BJI2D4LE5C2JSL.json","graph_json":"https://pith.science/api/pith-number/ZDYPJWLIN3K3BJI2D4LE5C2JSL/graph.json","events_json":"https://pith.science/api/pith-number/ZDYPJWLIN3K3BJI2D4LE5C2JSL/events.json","paper":"https://pith.science/paper/ZDYPJWLI"},"agent_actions":{"view_html":"https://pith.science/pith/ZDYPJWLIN3K3BJI2D4LE5C2JSL","download_json":"https://pith.science/pith/ZDYPJWLIN3K3BJI2D4LE5C2JSL.json","view_paper":"https://pith.science/paper/ZDYPJWLI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.05394&json=true","fetch_graph":"https://pith.science/api/pith-number/ZDYPJWLIN3K3BJI2D4LE5C2JSL/graph.json","fetch_events":"https://pith.science/api/pith-number/ZDYPJWLIN3K3BJI2D4LE5C2JSL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZDYPJWLIN3K3BJI2D4LE5C2JSL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZDYPJWLIN3K3BJI2D4LE5C2JSL/action/storage_attestation","attest_author":"https://pith.science/pith/ZDYPJWLIN3K3BJI2D4LE5C2JSL/action/author_attestation","sign_citation":"https://pith.science/pith/ZDYPJWLIN3K3BJI2D4LE5C2JSL/action/citation_signature","submit_replication":"https://pith.science/pith/ZDYPJWLIN3K3BJI2D4LE5C2JSL/action/replication_record"}},"created_at":"2026-05-18T01:12:43.201139+00:00","updated_at":"2026-05-18T01:12:43.201139+00:00"}