{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:7QI6FLKYS6MGGMBQ7VC7GVFDFZ","short_pith_number":"pith:7QI6FLKY","schema_version":"1.0","canonical_sha256":"fc11e2ad589798633030fd45f354a32e7b00051e9edfbd08748daac7c1739766","source":{"kind":"arxiv","id":"1412.1619","version":3},"attestation_state":"computed","paper":{"title":"Fast Rates by Transferring from Auxiliary Hypotheses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Francesco Orabona, Ilja Kuzborskij","submitted_at":"2014-12-04T11:01:11Z","abstract_excerpt":"In this work we consider the learning setting where, in addition to the training set, the learner receives a collection of auxiliary hypotheses originating from other tasks. We focus on a broad class of ERM-based linear algorithms that can be instantiated with any non-negative smooth loss function and any strongly convex regularizer. We establish generalization and excess risk bounds, showing that, if the algorithm is fed with a good combination of source hypotheses, generalization happens at the fast rate $\\mathcal{O}(1/m)$ instead of the usual $\\mathcal{O}(1/\\sqrt{m})$. On the other hand, if"},"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":"1412.1619","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-04T11:01:11Z","cross_cats_sorted":[],"title_canon_sha256":"a2ad315f27a32d0e1608ac0bd4cb32974388c6af8ba6a7fe53bf2da4b562aeae","abstract_canon_sha256":"f92a841d78471a7722a64660ba471f41ba3ab1be054779cb496610fa7f5b0177"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:02:05.284773Z","signature_b64":"AkaMemWVmjOYHL7S7vEVHO9Fq2bP4zi/QyLaSbzM2AjbWOMKOLP16+j2i0GRLc/3mwq/xOPXamRA1W5SPonUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc11e2ad589798633030fd45f354a32e7b00051e9edfbd08748daac7c1739766","last_reissued_at":"2026-05-18T01:02:05.284261Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:02:05.284261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast Rates by Transferring from Auxiliary Hypotheses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Francesco Orabona, Ilja Kuzborskij","submitted_at":"2014-12-04T11:01:11Z","abstract_excerpt":"In this work we consider the learning setting where, in addition to the training set, the learner receives a collection of auxiliary hypotheses originating from other tasks. We focus on a broad class of ERM-based linear algorithms that can be instantiated with any non-negative smooth loss function and any strongly convex regularizer. We establish generalization and excess risk bounds, showing that, if the algorithm is fed with a good combination of source hypotheses, generalization happens at the fast rate $\\mathcal{O}(1/m)$ instead of the usual $\\mathcal{O}(1/\\sqrt{m})$. On the other hand, if"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.1619","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":""},"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":"1412.1619","created_at":"2026-05-18T01:02:05.284343+00:00"},{"alias_kind":"arxiv_version","alias_value":"1412.1619v3","created_at":"2026-05-18T01:02:05.284343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.1619","created_at":"2026-05-18T01:02:05.284343+00:00"},{"alias_kind":"pith_short_12","alias_value":"7QI6FLKYS6MG","created_at":"2026-05-18T12:28:19.803747+00:00"},{"alias_kind":"pith_short_16","alias_value":"7QI6FLKYS6MGGMBQ","created_at":"2026-05-18T12:28:19.803747+00:00"},{"alias_kind":"pith_short_8","alias_value":"7QI6FLKY","created_at":"2026-05-18T12:28:19.803747+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/7QI6FLKYS6MGGMBQ7VC7GVFDFZ","json":"https://pith.science/pith/7QI6FLKYS6MGGMBQ7VC7GVFDFZ.json","graph_json":"https://pith.science/api/pith-number/7QI6FLKYS6MGGMBQ7VC7GVFDFZ/graph.json","events_json":"https://pith.science/api/pith-number/7QI6FLKYS6MGGMBQ7VC7GVFDFZ/events.json","paper":"https://pith.science/paper/7QI6FLKY"},"agent_actions":{"view_html":"https://pith.science/pith/7QI6FLKYS6MGGMBQ7VC7GVFDFZ","download_json":"https://pith.science/pith/7QI6FLKYS6MGGMBQ7VC7GVFDFZ.json","view_paper":"https://pith.science/paper/7QI6FLKY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1412.1619&json=true","fetch_graph":"https://pith.science/api/pith-number/7QI6FLKYS6MGGMBQ7VC7GVFDFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/7QI6FLKYS6MGGMBQ7VC7GVFDFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7QI6FLKYS6MGGMBQ7VC7GVFDFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7QI6FLKYS6MGGMBQ7VC7GVFDFZ/action/storage_attestation","attest_author":"https://pith.science/pith/7QI6FLKYS6MGGMBQ7VC7GVFDFZ/action/author_attestation","sign_citation":"https://pith.science/pith/7QI6FLKYS6MGGMBQ7VC7GVFDFZ/action/citation_signature","submit_replication":"https://pith.science/pith/7QI6FLKYS6MGGMBQ7VC7GVFDFZ/action/replication_record"}},"created_at":"2026-05-18T01:02:05.284343+00:00","updated_at":"2026-05-18T01:02:05.284343+00:00"}