{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:S7CJ5HIQEVZTMW225ROHDOH4G6","short_pith_number":"pith:S7CJ5HIQ","schema_version":"1.0","canonical_sha256":"97c49e9d102573365b5aec5c71b8fc37bb78f3f0759f61fbfa68ad800f5880c6","source":{"kind":"arxiv","id":"1501.02629","version":4},"attestation_state":"computed","paper":{"title":"Scaling-up Empirical Risk Minimization: Optimization of Incomplete U-statistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Aur\\'elien Bellet, Igor Colin, St\\'ephan Cl\\'emen\\c{c}on","submitted_at":"2015-01-12T12:58:45Z","abstract_excerpt":"In a wide range of statistical learning problems such as ranking, clustering or metric learning among others, the risk is accurately estimated by $U$-statistics of degree $d\\geq 1$, i.e. functionals of the training data with low variance that take the form of averages over $k$-tuples. From a computational perspective, the calculation of such statistics is highly expensive even for a moderate sample size $n$, as it requires averaging $O(n^d)$ terms. This makes learning procedures relying on the optimization of such data functionals hardly feasible in practice. It is the major goal of this paper"},"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":"1501.02629","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-01-12T12:58:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"608794777306b59080d6e54a261157aeca6a5f947a26574ee6488a6768b31a48","abstract_canon_sha256":"a8bbab94754415f57f0a678b27d271e069e2461c933d91a222021dad09ecd9da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:39.159568Z","signature_b64":"rD/Td0OsCd/iGn+gkA1XO3Mmza304zD67MdhP9+HQ9KvHvICJ8dbMKk/+LOUzipUlN0IQghE7/Rm4/xvYMNODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97c49e9d102573365b5aec5c71b8fc37bb78f3f0759f61fbfa68ad800f5880c6","last_reissued_at":"2026-05-17T23:55:39.159117Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:39.159117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling-up Empirical Risk Minimization: Optimization of Incomplete U-statistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Aur\\'elien Bellet, Igor Colin, St\\'ephan Cl\\'emen\\c{c}on","submitted_at":"2015-01-12T12:58:45Z","abstract_excerpt":"In a wide range of statistical learning problems such as ranking, clustering or metric learning among others, the risk is accurately estimated by $U$-statistics of degree $d\\geq 1$, i.e. functionals of the training data with low variance that take the form of averages over $k$-tuples. From a computational perspective, the calculation of such statistics is highly expensive even for a moderate sample size $n$, as it requires averaging $O(n^d)$ terms. This makes learning procedures relying on the optimization of such data functionals hardly feasible in practice. It is the major goal of this paper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1501.02629","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1501.02629","created_at":"2026-05-17T23:55:39.159206+00:00"},{"alias_kind":"arxiv_version","alias_value":"1501.02629v4","created_at":"2026-05-17T23:55:39.159206+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1501.02629","created_at":"2026-05-17T23:55:39.159206+00:00"},{"alias_kind":"pith_short_12","alias_value":"S7CJ5HIQEVZT","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_16","alias_value":"S7CJ5HIQEVZTMW22","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_8","alias_value":"S7CJ5HIQ","created_at":"2026-05-18T12:29:39.896362+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/S7CJ5HIQEVZTMW225ROHDOH4G6","json":"https://pith.science/pith/S7CJ5HIQEVZTMW225ROHDOH4G6.json","graph_json":"https://pith.science/api/pith-number/S7CJ5HIQEVZTMW225ROHDOH4G6/graph.json","events_json":"https://pith.science/api/pith-number/S7CJ5HIQEVZTMW225ROHDOH4G6/events.json","paper":"https://pith.science/paper/S7CJ5HIQ"},"agent_actions":{"view_html":"https://pith.science/pith/S7CJ5HIQEVZTMW225ROHDOH4G6","download_json":"https://pith.science/pith/S7CJ5HIQEVZTMW225ROHDOH4G6.json","view_paper":"https://pith.science/paper/S7CJ5HIQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1501.02629&json=true","fetch_graph":"https://pith.science/api/pith-number/S7CJ5HIQEVZTMW225ROHDOH4G6/graph.json","fetch_events":"https://pith.science/api/pith-number/S7CJ5HIQEVZTMW225ROHDOH4G6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S7CJ5HIQEVZTMW225ROHDOH4G6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S7CJ5HIQEVZTMW225ROHDOH4G6/action/storage_attestation","attest_author":"https://pith.science/pith/S7CJ5HIQEVZTMW225ROHDOH4G6/action/author_attestation","sign_citation":"https://pith.science/pith/S7CJ5HIQEVZTMW225ROHDOH4G6/action/citation_signature","submit_replication":"https://pith.science/pith/S7CJ5HIQEVZTMW225ROHDOH4G6/action/replication_record"}},"created_at":"2026-05-17T23:55:39.159206+00:00","updated_at":"2026-05-17T23:55:39.159206+00:00"}