{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:3NZRDKZWKJY5WDILM3XQLQU66H","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"abb981a58874e8a5a8bfdc0e80a4389d1b8e6b8bef6e1702498f8ef1975902d6","cross_cats_sorted":["cs.AI","cs.IR","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-24T16:37:07Z","title_canon_sha256":"38dfbd69a168565bbe9f197fbe4fdef96446a47d941930c87a55e7953113489a"},"schema_version":"1.0","source":{"id":"2202.12183","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.12183","created_at":"2026-07-05T05:38:20Z"},{"alias_kind":"arxiv_version","alias_value":"2202.12183v5","created_at":"2026-07-05T05:38:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.12183","created_at":"2026-07-05T05:38:20Z"},{"alias_kind":"pith_short_12","alias_value":"3NZRDKZWKJY5","created_at":"2026-07-05T05:38:20Z"},{"alias_kind":"pith_short_16","alias_value":"3NZRDKZWKJY5WDIL","created_at":"2026-07-05T05:38:20Z"},{"alias_kind":"pith_short_8","alias_value":"3NZRDKZW","created_at":"2026-07-05T05:38:20Z"}],"graph_snapshots":[{"event_id":"sha256:243430deabd9f0798fee066d7cb82b2d14b7d0bfa93975ea6938eabe9f189510","target":"graph","created_at":"2026-07-05T05:38:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2202.12183/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"NDCG, namely Normalized Discounted Cumulative Gain, is a widely used ranking metric in information retrieval and machine learning. However, efficient and provable stochastic methods for maximizing NDCG are still lacking, especially for deep models. In this paper, we propose a principled approach to optimize NDCG and its top-$K$ variant. First, we formulate a novel compositional optimization problem for optimizing the NDCG surrogate, and a novel bilevel compositional optimization problem for optimizing the top-$K$ NDCG surrogate. Then, we develop efficient stochastic algorithms with provable co","authors_text":"Lijun Zhang, Quanqi Hu, Tianbao Yang, Yongjian Zhong, Zi-Hao Qiu","cross_cats":["cs.AI","cs.IR","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-24T16:37:07Z","title":"Large-scale Stochastic Optimization of NDCG Surrogates for Deep Learning with Provable Convergence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.12183","kind":"arxiv","version":5},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f42e3d6adfec5721ecc9d18c92e70318c67978106d1e961aebf060f4866740fc","target":"record","created_at":"2026-07-05T05:38:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"abb981a58874e8a5a8bfdc0e80a4389d1b8e6b8bef6e1702498f8ef1975902d6","cross_cats_sorted":["cs.AI","cs.IR","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-24T16:37:07Z","title_canon_sha256":"38dfbd69a168565bbe9f197fbe4fdef96446a47d941930c87a55e7953113489a"},"schema_version":"1.0","source":{"id":"2202.12183","kind":"arxiv","version":5}},"canonical_sha256":"db7311ab365271db0d0b66ef05c29ef1d1b4d35043a30ed5c3e0225772716fda","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db7311ab365271db0d0b66ef05c29ef1d1b4d35043a30ed5c3e0225772716fda","first_computed_at":"2026-07-05T05:38:20.824276Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:38:20.824276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gD/AftiLN5LnXspOUuH1FoHm+NfNsP1smDCYV2JeGFvZ0P1cvK6XoPR/XqDr8qFfFVsB046g7DM4XFGC/oitCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:38:20.824761Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.12183","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f42e3d6adfec5721ecc9d18c92e70318c67978106d1e961aebf060f4866740fc","sha256:243430deabd9f0798fee066d7cb82b2d14b7d0bfa93975ea6938eabe9f189510"],"state_sha256":"8867feb9363bd2ab5c0599a392d4ef66906b1eccc3c7d207bc286c9b8533cedf"}