{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:XB3L54ATUJQ2525F6XYDFWBGKJ","short_pith_number":"pith:XB3L54AT","schema_version":"1.0","canonical_sha256":"b876bef013a261aeeba5f5f032d826525a20f7eb5208ef2c8be3d7e9a0d90bf9","source":{"kind":"arxiv","id":"1705.07152","version":3},"attestation_state":"computed","paper":{"title":"Data-driven Optimal Cost Selection for Distributionally Robust Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Fan Zhang, Jose Blanchet, Karthyek Murthy, Yang Kang","submitted_at":"2017-05-19T19:16:55Z","abstract_excerpt":"Recently, (Blanchet, Kang, and Murhy 2016, and Blanchet, and Kang 2017) showed that several machine learning algorithms, such as square-root Lasso, Support Vector Machines, and regularized logistic regression, among many others, can be represented exactly as distributionally robust optimization (DRO) problems. The distributional uncertainty is defined as a neighborhood centered at the empirical distribution. We propose a methodology which learns such neighborhood in a natural data-driven way. We show rigorously that our framework encompasses adaptive regularization as a particular case. Moreov"},"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":"1705.07152","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-19T19:16:55Z","cross_cats_sorted":[],"title_canon_sha256":"e713883bbb2da9515186cc9a4af67ec47cf5cb89d192791f91715b7f311312ec","abstract_canon_sha256":"62642f0d15b6d3fbfd48f56942bef49ba6f28fc40bdb4e5777a48c7ec893e615"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:42:57.436770Z","signature_b64":"c3ZHkvIiMVX3kVQscQWu+MOWOzgOLhioIDw0+r5CMkKu5Wjt9sjiednmNc4uka9kK68WWhzG5frA4Olroqy9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b876bef013a261aeeba5f5f032d826525a20f7eb5208ef2c8be3d7e9a0d90bf9","last_reissued_at":"2026-07-05T00:42:57.436377Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:42:57.436377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-driven Optimal Cost Selection for Distributionally Robust Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Fan Zhang, Jose Blanchet, Karthyek Murthy, Yang Kang","submitted_at":"2017-05-19T19:16:55Z","abstract_excerpt":"Recently, (Blanchet, Kang, and Murhy 2016, and Blanchet, and Kang 2017) showed that several machine learning algorithms, such as square-root Lasso, Support Vector Machines, and regularized logistic regression, among many others, can be represented exactly as distributionally robust optimization (DRO) problems. The distributional uncertainty is defined as a neighborhood centered at the empirical distribution. We propose a methodology which learns such neighborhood in a natural data-driven way. We show rigorously that our framework encompasses adaptive regularization as a particular case. Moreov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07152","kind":"arxiv","version":3},"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/1705.07152/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":"1705.07152","created_at":"2026-07-05T00:42:57.436428+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.07152v3","created_at":"2026-07-05T00:42:57.436428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07152","created_at":"2026-07-05T00:42:57.436428+00:00"},{"alias_kind":"pith_short_12","alias_value":"XB3L54ATUJQ2","created_at":"2026-07-05T00:42:57.436428+00:00"},{"alias_kind":"pith_short_16","alias_value":"XB3L54ATUJQ2525F","created_at":"2026-07-05T00:42:57.436428+00:00"},{"alias_kind":"pith_short_8","alias_value":"XB3L54AT","created_at":"2026-07-05T00:42:57.436428+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.08729","citing_title":"Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learning","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XB3L54ATUJQ2525F6XYDFWBGKJ","json":"https://pith.science/pith/XB3L54ATUJQ2525F6XYDFWBGKJ.json","graph_json":"https://pith.science/api/pith-number/XB3L54ATUJQ2525F6XYDFWBGKJ/graph.json","events_json":"https://pith.science/api/pith-number/XB3L54ATUJQ2525F6XYDFWBGKJ/events.json","paper":"https://pith.science/paper/XB3L54AT"},"agent_actions":{"view_html":"https://pith.science/pith/XB3L54ATUJQ2525F6XYDFWBGKJ","download_json":"https://pith.science/pith/XB3L54ATUJQ2525F6XYDFWBGKJ.json","view_paper":"https://pith.science/paper/XB3L54AT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.07152&json=true","fetch_graph":"https://pith.science/api/pith-number/XB3L54ATUJQ2525F6XYDFWBGKJ/graph.json","fetch_events":"https://pith.science/api/pith-number/XB3L54ATUJQ2525F6XYDFWBGKJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XB3L54ATUJQ2525F6XYDFWBGKJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XB3L54ATUJQ2525F6XYDFWBGKJ/action/storage_attestation","attest_author":"https://pith.science/pith/XB3L54ATUJQ2525F6XYDFWBGKJ/action/author_attestation","sign_citation":"https://pith.science/pith/XB3L54ATUJQ2525F6XYDFWBGKJ/action/citation_signature","submit_replication":"https://pith.science/pith/XB3L54ATUJQ2525F6XYDFWBGKJ/action/replication_record"}},"created_at":"2026-07-05T00:42:57.436428+00:00","updated_at":"2026-07-05T00:42:57.436428+00:00"}