{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QLE64HXUPJWRH452ZJ2VTRPEKK","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":"0ddd4f9f9f97b5cf37f704d9c371f6afb2535167c1ab4720fa411e0adb1aa227","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-28T17:02:49Z","title_canon_sha256":"ac35c9ffdfd45bc33b9891fb496139d2d97aecb21ed5286d4cd63259f9c172f6"},"schema_version":"1.0","source":{"id":"1908.10831","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.10831","created_at":"2026-07-05T01:14:27Z"},{"alias_kind":"arxiv_version","alias_value":"1908.10831v5","created_at":"2026-07-05T01:14:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.10831","created_at":"2026-07-05T01:14:27Z"},{"alias_kind":"pith_short_12","alias_value":"QLE64HXUPJWR","created_at":"2026-07-05T01:14:27Z"},{"alias_kind":"pith_short_16","alias_value":"QLE64HXUPJWRH452","created_at":"2026-07-05T01:14:27Z"},{"alias_kind":"pith_short_8","alias_value":"QLE64HXU","created_at":"2026-07-05T01:14:27Z"}],"graph_snapshots":[{"event_id":"sha256:806489e328fb17bfc1f42ce589185fa54555e8061815dcb51e5a3cd556033f5e","target":"graph","created_at":"2026-07-05T01:14:27Z","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/1908.10831/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Stochastic AUC maximization has garnered an increasing interest due to better fit to imbalanced data classification. However, existing works are limited to stochastic AUC maximization with a linear predictive model, which restricts its predictive power when dealing with extremely complex data. In this paper, we consider stochastic AUC maximization problem with a deep neural network as the predictive model. Building on the saddle point reformulation of a surrogated loss of AUC, the problem can be cast into a {\\it non-convex concave} min-max problem. The main contribution made in this paper is t","authors_text":"Mingrui Liu, Tianbao Yang, Yiming Ying, Zhuoning Yuan","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-28T17:02:49Z","title":"Stochastic AUC Maximization with Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.10831","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":"sha256:6d5f211ad376a5362d501fab98d5a930fb0b182873f82cc00fdc18f2049c5fbb","target":"record","created_at":"2026-07-05T01:14:27Z","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":"0ddd4f9f9f97b5cf37f704d9c371f6afb2535167c1ab4720fa411e0adb1aa227","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-28T17:02:49Z","title_canon_sha256":"ac35c9ffdfd45bc33b9891fb496139d2d97aecb21ed5286d4cd63259f9c172f6"},"schema_version":"1.0","source":{"id":"1908.10831","kind":"arxiv","version":5}},"canonical_sha256":"82c9ee1ef47a6d13f3baca7559c5e452a24ecfaeda0e91723d3d3af46d7eeb6b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"82c9ee1ef47a6d13f3baca7559c5e452a24ecfaeda0e91723d3d3af46d7eeb6b","first_computed_at":"2026-07-05T01:14:27.886041Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:14:27.886041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B3E2odLIQTCgrHAQa1qfLY0D++geDsiFUIzt7VYvyq+nuhO4rU2znUk/Mc86wSrYkJG73uTnR16/mJRNceT+CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:14:27.886446Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.10831","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d5f211ad376a5362d501fab98d5a930fb0b182873f82cc00fdc18f2049c5fbb","sha256:806489e328fb17bfc1f42ce589185fa54555e8061815dcb51e5a3cd556033f5e"],"state_sha256":"e0483031f0fafc687741d3e784a81fd0bfa95aca2cfc2a5b5bfe95f2573f76ef"}