{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:S6V27YH7WSPF3XYPKP3F6VHJO2","short_pith_number":"pith:S6V27YH7","schema_version":"1.0","canonical_sha256":"97abafe0ffb49e5ddf0f53f65f54e976822066b7b2d3b50e1bce4b72181bd000","source":{"kind":"arxiv","id":"2203.13225","version":1},"attestation_state":"computed","paper":{"title":"Distributionally Robust Optimization via Ball Oracle Acceleration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.LG"],"primary_cat":"math.OC","authors_text":"Danielle Hausler, Yair Carmon","submitted_at":"2022-03-24T17:31:43Z","abstract_excerpt":"We develop and analyze algorithms for distributionally robust optimization (DRO) of convex losses. In particular, we consider group-structured and bounded $f$-divergence uncertainty sets. Our approach relies on an accelerated method that queries a ball optimization oracle, i.e., a subroutine that minimizes the objective within a small ball around the query point. Our main contribution is efficient implementations of this oracle for DRO objectives. For DRO with $N$ non-smooth loss functions, the resulting algorithms find an $\\epsilon$-accurate solution with $\\widetilde{O}\\left(N\\epsilon^{-2/3} "},"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":"2203.13225","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-03-24T17:31:43Z","cross_cats_sorted":["cs.DS","cs.LG"],"title_canon_sha256":"3e092771a3fdc4bf630940e2eb96a1664c1c18a14c0a8d38ec9784d5abc1fc4d","abstract_canon_sha256":"a91ee69bb9aedcec1fb3bb67b9c402437a582ac4764ae591209766c5a2f0b658"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:21.989149Z","signature_b64":"lJIpPJ3ShKnagktm5qd/m970cZ5TPt3dUvEMuDtD67VsVJBX+zhQvXi9BszsTX+uDf2XU00nDDRheYa/8FS2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97abafe0ffb49e5ddf0f53f65f54e976822066b7b2d3b50e1bce4b72181bd000","last_reissued_at":"2026-07-05T04:08:21.988742Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:21.988742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributionally Robust Optimization via Ball Oracle Acceleration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.LG"],"primary_cat":"math.OC","authors_text":"Danielle Hausler, Yair Carmon","submitted_at":"2022-03-24T17:31:43Z","abstract_excerpt":"We develop and analyze algorithms for distributionally robust optimization (DRO) of convex losses. In particular, we consider group-structured and bounded $f$-divergence uncertainty sets. Our approach relies on an accelerated method that queries a ball optimization oracle, i.e., a subroutine that minimizes the objective within a small ball around the query point. Our main contribution is efficient implementations of this oracle for DRO objectives. For DRO with $N$ non-smooth loss functions, the resulting algorithms find an $\\epsilon$-accurate solution with $\\widetilde{O}\\left(N\\epsilon^{-2/3} "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.13225","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/2203.13225/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":"2203.13225","created_at":"2026-07-05T04:08:21.988800+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.13225v1","created_at":"2026-07-05T04:08:21.988800+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.13225","created_at":"2026-07-05T04:08:21.988800+00:00"},{"alias_kind":"pith_short_12","alias_value":"S6V27YH7WSPF","created_at":"2026-07-05T04:08:21.988800+00:00"},{"alias_kind":"pith_short_16","alias_value":"S6V27YH7WSPF3XYP","created_at":"2026-07-05T04:08:21.988800+00:00"},{"alias_kind":"pith_short_8","alias_value":"S6V27YH7","created_at":"2026-07-05T04:08:21.988800+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/S6V27YH7WSPF3XYPKP3F6VHJO2","json":"https://pith.science/pith/S6V27YH7WSPF3XYPKP3F6VHJO2.json","graph_json":"https://pith.science/api/pith-number/S6V27YH7WSPF3XYPKP3F6VHJO2/graph.json","events_json":"https://pith.science/api/pith-number/S6V27YH7WSPF3XYPKP3F6VHJO2/events.json","paper":"https://pith.science/paper/S6V27YH7"},"agent_actions":{"view_html":"https://pith.science/pith/S6V27YH7WSPF3XYPKP3F6VHJO2","download_json":"https://pith.science/pith/S6V27YH7WSPF3XYPKP3F6VHJO2.json","view_paper":"https://pith.science/paper/S6V27YH7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.13225&json=true","fetch_graph":"https://pith.science/api/pith-number/S6V27YH7WSPF3XYPKP3F6VHJO2/graph.json","fetch_events":"https://pith.science/api/pith-number/S6V27YH7WSPF3XYPKP3F6VHJO2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S6V27YH7WSPF3XYPKP3F6VHJO2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S6V27YH7WSPF3XYPKP3F6VHJO2/action/storage_attestation","attest_author":"https://pith.science/pith/S6V27YH7WSPF3XYPKP3F6VHJO2/action/author_attestation","sign_citation":"https://pith.science/pith/S6V27YH7WSPF3XYPKP3F6VHJO2/action/citation_signature","submit_replication":"https://pith.science/pith/S6V27YH7WSPF3XYPKP3F6VHJO2/action/replication_record"}},"created_at":"2026-07-05T04:08:21.988800+00:00","updated_at":"2026-07-05T04:08:21.988800+00:00"}