{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QGHQWM6FJEYMGBIDIZPWGFVKAO","short_pith_number":"pith:QGHQWM6F","schema_version":"1.0","canonical_sha256":"818f0b33c54930c30503465f6316aa03bcec9597128f48910c7f3f0efa37f0cb","source":{"kind":"arxiv","id":"2503.22923","version":2},"attestation_state":"computed","paper":{"title":"Nested Stochastic Algorithm for Generalized Sinkhorn distance-Regularized Distributionally Robust Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Yi Zhou, Yufeng Yang, Zhaosong Lu","submitted_at":"2025-03-29T01:01:02Z","abstract_excerpt":"Distributionally robust optimization (DRO) is a powerful technique to train robust models against data distribution shift. This paper aims to solve regularized nonconvex DRO problems, where the uncertainty set is modeled by a so-called generalized Sinkhorn distance and the loss function is nonconvex and possibly unbounded. Such a distance allows to model uncertainty of distributions with different probability supports and divergence functions. For this class of regularized DRO problems, we derive a novel dual formulation taking the form of nested stochastic optimization, where the dual variabl"},"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":"2503.22923","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-03-29T01:01:02Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"56977c8389ca4962491b5561f86d0f7a2cdb935b5977a0fa47bc671f9520dfbe","abstract_canon_sha256":"2e029a22c7d2c7eccb4cb853de667710e9b7f307b618addbe54ec5a285a13d76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:53.534203Z","signature_b64":"w0zwOB7kTGxLTkv33Hkf/s1vwjvmp9kVKZECDH6yQykTYmaFIXM0dnQkMkBInVmhFbEFjhvKEobSyQVy9PSlBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"818f0b33c54930c30503465f6316aa03bcec9597128f48910c7f3f0efa37f0cb","last_reissued_at":"2026-07-05T11:27:53.533704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:53.533704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nested Stochastic Algorithm for Generalized Sinkhorn distance-Regularized Distributionally Robust Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Yi Zhou, Yufeng Yang, Zhaosong Lu","submitted_at":"2025-03-29T01:01:02Z","abstract_excerpt":"Distributionally robust optimization (DRO) is a powerful technique to train robust models against data distribution shift. This paper aims to solve regularized nonconvex DRO problems, where the uncertainty set is modeled by a so-called generalized Sinkhorn distance and the loss function is nonconvex and possibly unbounded. Such a distance allows to model uncertainty of distributions with different probability supports and divergence functions. For this class of regularized DRO problems, we derive a novel dual formulation taking the form of nested stochastic optimization, where the dual variabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22923","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/2503.22923/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":"2503.22923","created_at":"2026-07-05T11:27:53.533765+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.22923v2","created_at":"2026-07-05T11:27:53.533765+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22923","created_at":"2026-07-05T11:27:53.533765+00:00"},{"alias_kind":"pith_short_12","alias_value":"QGHQWM6FJEYM","created_at":"2026-07-05T11:27:53.533765+00:00"},{"alias_kind":"pith_short_16","alias_value":"QGHQWM6FJEYMGBID","created_at":"2026-07-05T11:27:53.533765+00:00"},{"alias_kind":"pith_short_8","alias_value":"QGHQWM6F","created_at":"2026-07-05T11:27:53.533765+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QGHQWM6FJEYMGBIDIZPWGFVKAO","json":"https://pith.science/pith/QGHQWM6FJEYMGBIDIZPWGFVKAO.json","graph_json":"https://pith.science/api/pith-number/QGHQWM6FJEYMGBIDIZPWGFVKAO/graph.json","events_json":"https://pith.science/api/pith-number/QGHQWM6FJEYMGBIDIZPWGFVKAO/events.json","paper":"https://pith.science/paper/QGHQWM6F"},"agent_actions":{"view_html":"https://pith.science/pith/QGHQWM6FJEYMGBIDIZPWGFVKAO","download_json":"https://pith.science/pith/QGHQWM6FJEYMGBIDIZPWGFVKAO.json","view_paper":"https://pith.science/paper/QGHQWM6F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.22923&json=true","fetch_graph":"https://pith.science/api/pith-number/QGHQWM6FJEYMGBIDIZPWGFVKAO/graph.json","fetch_events":"https://pith.science/api/pith-number/QGHQWM6FJEYMGBIDIZPWGFVKAO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QGHQWM6FJEYMGBIDIZPWGFVKAO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QGHQWM6FJEYMGBIDIZPWGFVKAO/action/storage_attestation","attest_author":"https://pith.science/pith/QGHQWM6FJEYMGBIDIZPWGFVKAO/action/author_attestation","sign_citation":"https://pith.science/pith/QGHQWM6FJEYMGBIDIZPWGFVKAO/action/citation_signature","submit_replication":"https://pith.science/pith/QGHQWM6FJEYMGBIDIZPWGFVKAO/action/replication_record"}},"created_at":"2026-07-05T11:27:53.533765+00:00","updated_at":"2026-07-05T11:27:53.533765+00:00"}