{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SJBZOUBI3D4YHEU4TAPXXFCGIG","short_pith_number":"pith:SJBZOUBI","schema_version":"1.0","canonical_sha256":"9243975028d8f983929c981f7b944641907eba0d9b858de1e896e9ee777fb80f","source":{"kind":"arxiv","id":"2309.04557","version":2},"attestation_state":"computed","paper":{"title":"Regret-Optimal Federated Transfer Learning for Kernel Regression with Applications in American Option Pricing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.DS","math.OC","q-fin.CP"],"primary_cat":"cs.LG","authors_text":"Anastasis Kratsios, Aurelien Lucchi, Florian Krach, Matheus Grasselli, Xuwei Yang","submitted_at":"2023-09-08T19:17:03Z","abstract_excerpt":"We propose an optimal iterative scheme for federated transfer learning, where a central planner has access to datasets ${\\cal D}_1,\\dots,{\\cal D}_N$ for the same learning model $f_{\\theta}$. Our objective is to minimize the cumulative deviation of the generated parameters $\\{\\theta_i(t)\\}_{t=0}^T$ across all $T$ iterations from the specialized parameters $\\theta^\\star_{1},\\ldots,\\theta^\\star_N$ obtained for each dataset, while respecting the loss function for the model $f_{\\theta(T)}$ produced by the algorithm upon halting. We only allow for continual communication between each of the speciali"},"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":"2309.04557","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-08T19:17:03Z","cross_cats_sorted":["math.DS","math.OC","q-fin.CP"],"title_canon_sha256":"e794c9d3e4f598d42898f33dd10e7377e00a3d51e6460271dae0385c7aef00e0","abstract_canon_sha256":"9416a01a5d332a7c0d56559b30dcfa65f84db19bcc1df3c6c746f1beac1a9f7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:06.617885Z","signature_b64":"+VyqD3E0/QTLalh8zuzKJg7pbDxFDey2sB0Q/EP/YtpWRm5TFAXb4SfNJ06DEfMEwJU2PTmSP0RFzPXMpkwEDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9243975028d8f983929c981f7b944641907eba0d9b858de1e896e9ee777fb80f","last_reissued_at":"2026-07-05T09:15:06.617448Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:06.617448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regret-Optimal Federated Transfer Learning for Kernel Regression with Applications in American Option Pricing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.DS","math.OC","q-fin.CP"],"primary_cat":"cs.LG","authors_text":"Anastasis Kratsios, Aurelien Lucchi, Florian Krach, Matheus Grasselli, Xuwei Yang","submitted_at":"2023-09-08T19:17:03Z","abstract_excerpt":"We propose an optimal iterative scheme for federated transfer learning, where a central planner has access to datasets ${\\cal D}_1,\\dots,{\\cal D}_N$ for the same learning model $f_{\\theta}$. Our objective is to minimize the cumulative deviation of the generated parameters $\\{\\theta_i(t)\\}_{t=0}^T$ across all $T$ iterations from the specialized parameters $\\theta^\\star_{1},\\ldots,\\theta^\\star_N$ obtained for each dataset, while respecting the loss function for the model $f_{\\theta(T)}$ produced by the algorithm upon halting. We only allow for continual communication between each of the speciali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04557","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/2309.04557/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":"2309.04557","created_at":"2026-07-05T09:15:06.617517+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.04557v2","created_at":"2026-07-05T09:15:06.617517+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04557","created_at":"2026-07-05T09:15:06.617517+00:00"},{"alias_kind":"pith_short_12","alias_value":"SJBZOUBI3D4Y","created_at":"2026-07-05T09:15:06.617517+00:00"},{"alias_kind":"pith_short_16","alias_value":"SJBZOUBI3D4YHEU4","created_at":"2026-07-05T09:15:06.617517+00:00"},{"alias_kind":"pith_short_8","alias_value":"SJBZOUBI","created_at":"2026-07-05T09:15:06.617517+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2312.08410","citing_title":"Universal approximation property of Banach space-valued random feature models including random neural networks","ref_index":82,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SJBZOUBI3D4YHEU4TAPXXFCGIG","json":"https://pith.science/pith/SJBZOUBI3D4YHEU4TAPXXFCGIG.json","graph_json":"https://pith.science/api/pith-number/SJBZOUBI3D4YHEU4TAPXXFCGIG/graph.json","events_json":"https://pith.science/api/pith-number/SJBZOUBI3D4YHEU4TAPXXFCGIG/events.json","paper":"https://pith.science/paper/SJBZOUBI"},"agent_actions":{"view_html":"https://pith.science/pith/SJBZOUBI3D4YHEU4TAPXXFCGIG","download_json":"https://pith.science/pith/SJBZOUBI3D4YHEU4TAPXXFCGIG.json","view_paper":"https://pith.science/paper/SJBZOUBI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.04557&json=true","fetch_graph":"https://pith.science/api/pith-number/SJBZOUBI3D4YHEU4TAPXXFCGIG/graph.json","fetch_events":"https://pith.science/api/pith-number/SJBZOUBI3D4YHEU4TAPXXFCGIG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SJBZOUBI3D4YHEU4TAPXXFCGIG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SJBZOUBI3D4YHEU4TAPXXFCGIG/action/storage_attestation","attest_author":"https://pith.science/pith/SJBZOUBI3D4YHEU4TAPXXFCGIG/action/author_attestation","sign_citation":"https://pith.science/pith/SJBZOUBI3D4YHEU4TAPXXFCGIG/action/citation_signature","submit_replication":"https://pith.science/pith/SJBZOUBI3D4YHEU4TAPXXFCGIG/action/replication_record"}},"created_at":"2026-07-05T09:15:06.617517+00:00","updated_at":"2026-07-05T09:15:06.617517+00:00"}