{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6NNUPTTJPNPYHHSBBBLBEMBTVH","short_pith_number":"pith:6NNUPTTJ","schema_version":"1.0","canonical_sha256":"f35b47ce697b5f839e410856123033a9f0954a565e136a9bd3dbf2fb2b3a25ff","source":{"kind":"arxiv","id":"2103.01901","version":2},"attestation_state":"computed","paper":{"title":"Minimax Estimation for Personalized Federated Learning: An Alternative between FedAvg and Local Training?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Qi Long, Qinqing Zheng, Shuxiao Chen, Weijie J. Su","submitted_at":"2021-03-02T17:58:20Z","abstract_excerpt":"A widely recognized difficulty in federated learning arises from the statistical heterogeneity among clients: local datasets often originate from distinct yet not entirely unrelated probability distributions, and personalization is, therefore, necessary to achieve optimal results from each individual's perspective. In this paper, we show how the excess risks of personalized federated learning using a smooth, strongly convex loss depend on data heterogeneity from a minimax point of view, with a focus on the FedAvg algorithm (McMahan et al., 2017) and pure local training (i.e., clients solve emp"},"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":"2103.01901","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-03-02T17:58:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c5562dffba326bef6406cfaebfa02f1f40476049d9fffe7f4e613354c3057046","abstract_canon_sha256":"91d4177d7d2cd73d38018ee5e28978e962d24b5b99655788bb8871865d3509a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:08.841654Z","signature_b64":"Xsleqy18mOqxHilY3pb8ZxbXvvFi86ohLWDEhL5klxmob0cT1qPNLALdiesrUzLmnDSbKwO4lLvH3OeYQfzFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f35b47ce697b5f839e410856123033a9f0954a565e136a9bd3dbf2fb2b3a25ff","last_reissued_at":"2026-07-05T10:28:08.840660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:08.840660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Minimax Estimation for Personalized Federated Learning: An Alternative between FedAvg and Local Training?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Qi Long, Qinqing Zheng, Shuxiao Chen, Weijie J. Su","submitted_at":"2021-03-02T17:58:20Z","abstract_excerpt":"A widely recognized difficulty in federated learning arises from the statistical heterogeneity among clients: local datasets often originate from distinct yet not entirely unrelated probability distributions, and personalization is, therefore, necessary to achieve optimal results from each individual's perspective. In this paper, we show how the excess risks of personalized federated learning using a smooth, strongly convex loss depend on data heterogeneity from a minimax point of view, with a focus on the FedAvg algorithm (McMahan et al., 2017) and pure local training (i.e., clients solve emp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.01901","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/2103.01901/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":"2103.01901","created_at":"2026-07-05T10:28:08.840798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.01901v2","created_at":"2026-07-05T10:28:08.840798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.01901","created_at":"2026-07-05T10:28:08.840798+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NNUPTTJPNPY","created_at":"2026-07-05T10:28:08.840798+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NNUPTTJPNPYHHSB","created_at":"2026-07-05T10:28:08.840798+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NNUPTTJ","created_at":"2026-07-05T10:28:08.840798+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30615","citing_title":"Tuning-Free Efficient Estimation for Multi-Source Data via Covariance-Aware Shrinkage","ref_index":120,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6NNUPTTJPNPYHHSBBBLBEMBTVH","json":"https://pith.science/pith/6NNUPTTJPNPYHHSBBBLBEMBTVH.json","graph_json":"https://pith.science/api/pith-number/6NNUPTTJPNPYHHSBBBLBEMBTVH/graph.json","events_json":"https://pith.science/api/pith-number/6NNUPTTJPNPYHHSBBBLBEMBTVH/events.json","paper":"https://pith.science/paper/6NNUPTTJ"},"agent_actions":{"view_html":"https://pith.science/pith/6NNUPTTJPNPYHHSBBBLBEMBTVH","download_json":"https://pith.science/pith/6NNUPTTJPNPYHHSBBBLBEMBTVH.json","view_paper":"https://pith.science/paper/6NNUPTTJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.01901&json=true","fetch_graph":"https://pith.science/api/pith-number/6NNUPTTJPNPYHHSBBBLBEMBTVH/graph.json","fetch_events":"https://pith.science/api/pith-number/6NNUPTTJPNPYHHSBBBLBEMBTVH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NNUPTTJPNPYHHSBBBLBEMBTVH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NNUPTTJPNPYHHSBBBLBEMBTVH/action/storage_attestation","attest_author":"https://pith.science/pith/6NNUPTTJPNPYHHSBBBLBEMBTVH/action/author_attestation","sign_citation":"https://pith.science/pith/6NNUPTTJPNPYHHSBBBLBEMBTVH/action/citation_signature","submit_replication":"https://pith.science/pith/6NNUPTTJPNPYHHSBBBLBEMBTVH/action/replication_record"}},"created_at":"2026-07-05T10:28:08.840798+00:00","updated_at":"2026-07-05T10:28:08.840798+00:00"}