{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:T6ENK36PT4XMSBIZ55Q7XM3MUS","short_pith_number":"pith:T6ENK36P","schema_version":"1.0","canonical_sha256":"9f88d56fcf9f2ec90519ef61fbb36ca4be2c6d5718801219cc95316d946603f7","source":{"kind":"arxiv","id":"2207.05377","version":2},"attestation_state":"computed","paper":{"title":"On the Generalization for Transfer Learning: An Information-Theoretic Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.IT"],"primary_cat":"cs.IT","authors_text":"Jingge Zhu, Jonathan H. Manton, Uwe Aickelin, Xuetong Wu","submitted_at":"2022-07-12T08:20:41Z","abstract_excerpt":"Transfer learning, or domain adaptation, is concerned with machine learning problems in which training and testing data come from possibly different probability distributions. In this work, we give an information-theoretic analysis of the generalization error and excess risk of transfer learning algorithms. Our results suggest, perhaps as expected, that the Kullback-Leibler (KL) divergence $D(\\mu\\|\\mu')$ plays an important role in the characterizations where $\\mu$ and $\\mu'$ denote the distribution of the training data and the testing data, respectively. Specifically, we provide generalization"},"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":"2207.05377","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2022-07-12T08:20:41Z","cross_cats_sorted":["cs.LG","math.IT"],"title_canon_sha256":"4fbee26a2443f3a213bb51e6cce0be4a6e2342fe3205962bc22c459b15a8f2b6","abstract_canon_sha256":"3cd8826d259e705c7053a568d30326491c67d0fa71dbe8a4a61d64118bc090e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:13.898147Z","signature_b64":"EMWrekffJeXztDLfMhaEbO9jecLawpPnH2IiN6dS5tB2hO/QcJc6fieBY4m0GjlzUjVNkxDBsAWxD/vCllfsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f88d56fcf9f2ec90519ef61fbb36ca4be2c6d5718801219cc95316d946603f7","last_reissued_at":"2026-07-05T08:53:13.897754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:13.897754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Generalization for Transfer Learning: An Information-Theoretic Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.IT"],"primary_cat":"cs.IT","authors_text":"Jingge Zhu, Jonathan H. Manton, Uwe Aickelin, Xuetong Wu","submitted_at":"2022-07-12T08:20:41Z","abstract_excerpt":"Transfer learning, or domain adaptation, is concerned with machine learning problems in which training and testing data come from possibly different probability distributions. In this work, we give an information-theoretic analysis of the generalization error and excess risk of transfer learning algorithms. Our results suggest, perhaps as expected, that the Kullback-Leibler (KL) divergence $D(\\mu\\|\\mu')$ plays an important role in the characterizations where $\\mu$ and $\\mu'$ denote the distribution of the training data and the testing data, respectively. Specifically, we provide generalization"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.05377","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/2207.05377/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":"2207.05377","created_at":"2026-07-05T08:53:13.897811+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.05377v2","created_at":"2026-07-05T08:53:13.897811+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.05377","created_at":"2026-07-05T08:53:13.897811+00:00"},{"alias_kind":"pith_short_12","alias_value":"T6ENK36PT4XM","created_at":"2026-07-05T08:53:13.897811+00:00"},{"alias_kind":"pith_short_16","alias_value":"T6ENK36PT4XMSBIZ","created_at":"2026-07-05T08:53:13.897811+00:00"},{"alias_kind":"pith_short_8","alias_value":"T6ENK36P","created_at":"2026-07-05T08:53:13.897811+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00849","citing_title":"Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T6ENK36PT4XMSBIZ55Q7XM3MUS","json":"https://pith.science/pith/T6ENK36PT4XMSBIZ55Q7XM3MUS.json","graph_json":"https://pith.science/api/pith-number/T6ENK36PT4XMSBIZ55Q7XM3MUS/graph.json","events_json":"https://pith.science/api/pith-number/T6ENK36PT4XMSBIZ55Q7XM3MUS/events.json","paper":"https://pith.science/paper/T6ENK36P"},"agent_actions":{"view_html":"https://pith.science/pith/T6ENK36PT4XMSBIZ55Q7XM3MUS","download_json":"https://pith.science/pith/T6ENK36PT4XMSBIZ55Q7XM3MUS.json","view_paper":"https://pith.science/paper/T6ENK36P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.05377&json=true","fetch_graph":"https://pith.science/api/pith-number/T6ENK36PT4XMSBIZ55Q7XM3MUS/graph.json","fetch_events":"https://pith.science/api/pith-number/T6ENK36PT4XMSBIZ55Q7XM3MUS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T6ENK36PT4XMSBIZ55Q7XM3MUS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T6ENK36PT4XMSBIZ55Q7XM3MUS/action/storage_attestation","attest_author":"https://pith.science/pith/T6ENK36PT4XMSBIZ55Q7XM3MUS/action/author_attestation","sign_citation":"https://pith.science/pith/T6ENK36PT4XMSBIZ55Q7XM3MUS/action/citation_signature","submit_replication":"https://pith.science/pith/T6ENK36PT4XMSBIZ55Q7XM3MUS/action/replication_record"}},"created_at":"2026-07-05T08:53:13.897811+00:00","updated_at":"2026-07-05T08:53:13.897811+00:00"}