{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:I2DVFSGAAUAU22AFOWA2PEORFY","short_pith_number":"pith:I2DVFSGA","schema_version":"1.0","canonical_sha256":"468752c8c005014d68057581a791d12e173889d26d32483000d5fb2747f9097c","source":{"kind":"arxiv","id":"2406.07585","version":2},"attestation_state":"computed","paper":{"title":"Rate-Preserving Reductions for Blackwell Approachability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Balasubramanian Sivan, Christoph Dann, Jon Schneider, Mehryar Mohri, Yishay Mansour","submitted_at":"2024-06-10T23:23:52Z","abstract_excerpt":"Abernethy et al. (2011) showed that Blackwell approachability and no-regret learning are equivalent, in the sense that any algorithm that solves a specific Blackwell approachability instance can be converted to a sublinear regret algorithm for a specific no-regret learning instance, and vice versa. In this paper, we study a more fine-grained form of such reductions, and ask when this translation between problems preserves not only a sublinear rate of convergence, but also preserves the optimal rate of convergence. That is, in which cases does it suffice to find the optimal regret bound for a n"},"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":"2406.07585","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-06-10T23:23:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4bd2a198aaecbd4d5654374244c1fd21a40c7f52310a584d925e03512c80a63d","abstract_canon_sha256":"53d6eac04637128d1f58291f6467306252a7e4f5c4e71a3d9a3246386dd7868f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:55.142466Z","signature_b64":"Pr1jlIuBznh0fLcdYuDGFJ1hyOL6F39wAiu2gEVXQH4PyF4fhp6XgA7wtG0P1ZE76vr1xRWjOa9s36VodPGGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"468752c8c005014d68057581a791d12e173889d26d32483000d5fb2747f9097c","last_reissued_at":"2026-07-05T08:44:55.142031Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:55.142031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rate-Preserving Reductions for Blackwell Approachability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Balasubramanian Sivan, Christoph Dann, Jon Schneider, Mehryar Mohri, Yishay Mansour","submitted_at":"2024-06-10T23:23:52Z","abstract_excerpt":"Abernethy et al. (2011) showed that Blackwell approachability and no-regret learning are equivalent, in the sense that any algorithm that solves a specific Blackwell approachability instance can be converted to a sublinear regret algorithm for a specific no-regret learning instance, and vice versa. In this paper, we study a more fine-grained form of such reductions, and ask when this translation between problems preserves not only a sublinear rate of convergence, but also preserves the optimal rate of convergence. That is, in which cases does it suffice to find the optimal regret bound for a n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07585","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/2406.07585/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":"2406.07585","created_at":"2026-07-05T08:44:55.142090+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07585v2","created_at":"2026-07-05T08:44:55.142090+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07585","created_at":"2026-07-05T08:44:55.142090+00:00"},{"alias_kind":"pith_short_12","alias_value":"I2DVFSGAAUAU","created_at":"2026-07-05T08:44:55.142090+00:00"},{"alias_kind":"pith_short_16","alias_value":"I2DVFSGAAUAU22AF","created_at":"2026-07-05T08:44:55.142090+00:00"},{"alias_kind":"pith_short_8","alias_value":"I2DVFSGA","created_at":"2026-07-05T08:44:55.142090+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.04543","citing_title":"Sparsity-Based Interpolation of External, Internal and Swap Regret","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I2DVFSGAAUAU22AFOWA2PEORFY","json":"https://pith.science/pith/I2DVFSGAAUAU22AFOWA2PEORFY.json","graph_json":"https://pith.science/api/pith-number/I2DVFSGAAUAU22AFOWA2PEORFY/graph.json","events_json":"https://pith.science/api/pith-number/I2DVFSGAAUAU22AFOWA2PEORFY/events.json","paper":"https://pith.science/paper/I2DVFSGA"},"agent_actions":{"view_html":"https://pith.science/pith/I2DVFSGAAUAU22AFOWA2PEORFY","download_json":"https://pith.science/pith/I2DVFSGAAUAU22AFOWA2PEORFY.json","view_paper":"https://pith.science/paper/I2DVFSGA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07585&json=true","fetch_graph":"https://pith.science/api/pith-number/I2DVFSGAAUAU22AFOWA2PEORFY/graph.json","fetch_events":"https://pith.science/api/pith-number/I2DVFSGAAUAU22AFOWA2PEORFY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I2DVFSGAAUAU22AFOWA2PEORFY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I2DVFSGAAUAU22AFOWA2PEORFY/action/storage_attestation","attest_author":"https://pith.science/pith/I2DVFSGAAUAU22AFOWA2PEORFY/action/author_attestation","sign_citation":"https://pith.science/pith/I2DVFSGAAUAU22AFOWA2PEORFY/action/citation_signature","submit_replication":"https://pith.science/pith/I2DVFSGAAUAU22AFOWA2PEORFY/action/replication_record"}},"created_at":"2026-07-05T08:44:55.142090+00:00","updated_at":"2026-07-05T08:44:55.142090+00:00"}