{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7IT2UGWGV7FILT4RWILFGSC2HS","short_pith_number":"pith:7IT2UGWG","schema_version":"1.0","canonical_sha256":"fa27aa1ac6afca85cf91b21653485a3cbfdfde468e4af101b4d9c61c8817d7eb","source":{"kind":"arxiv","id":"2002.10619","version":2},"attestation_state":"computed","paper":{"title":"Three Approaches for Personalization with Applications to Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ananda Theertha Suresh, Jae Ro, Mehryar Mohri, Yishay Mansour","submitted_at":"2020-02-25T01:36:43Z","abstract_excerpt":"The standard objective in machine learning is to train a single model for all users. However, in many learning scenarios, such as cloud computing and federated learning, it is possible to learn a personalized model per user. In this work, we present a systematic learning-theoretic study of personalization. We propose and analyze three approaches: user clustering, data interpolation, and model interpolation. For all three approaches, we provide learning-theoretic guarantees and efficient algorithms for which we also demonstrate the performance empirically. All of our algorithms are model-agnost"},"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":"2002.10619","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-25T01:36:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"24d205541f69468e56657a029fe448e17953f98489bc474e8c0b5a819237c197","abstract_canon_sha256":"e5cc246160deb037efd89ea407ce73ca0a49b2874808158583a5b8bcdb0d0f8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:20:15.629978Z","signature_b64":"J7rM47FR1svu21/zwQSVY9mnsnjVcv3Sd0GvTOmHLCb0bQq1ei6GQm9I9AMEsVBGlMIQ1L7LIPi4dZwYlLxcCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa27aa1ac6afca85cf91b21653485a3cbfdfde468e4af101b4d9c61c8817d7eb","last_reissued_at":"2026-07-05T01:20:15.629490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:20:15.629490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Three Approaches for Personalization with Applications to Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ananda Theertha Suresh, Jae Ro, Mehryar Mohri, Yishay Mansour","submitted_at":"2020-02-25T01:36:43Z","abstract_excerpt":"The standard objective in machine learning is to train a single model for all users. However, in many learning scenarios, such as cloud computing and federated learning, it is possible to learn a personalized model per user. In this work, we present a systematic learning-theoretic study of personalization. We propose and analyze three approaches: user clustering, data interpolation, and model interpolation. For all three approaches, we provide learning-theoretic guarantees and efficient algorithms for which we also demonstrate the performance empirically. All of our algorithms are model-agnost"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.10619","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/2002.10619/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":"2002.10619","created_at":"2026-07-05T01:20:15.629549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.10619v2","created_at":"2026-07-05T01:20:15.629549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.10619","created_at":"2026-07-05T01:20:15.629549+00:00"},{"alias_kind":"pith_short_12","alias_value":"7IT2UGWGV7FI","created_at":"2026-07-05T01:20:15.629549+00:00"},{"alias_kind":"pith_short_16","alias_value":"7IT2UGWGV7FILT4R","created_at":"2026-07-05T01:20:15.629549+00:00"},{"alias_kind":"pith_short_8","alias_value":"7IT2UGWG","created_at":"2026-07-05T01:20:15.629549+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"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":154,"is_internal_anchor":false},{"citing_arxiv_id":"2406.10861","citing_title":"Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2208.01618","citing_title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10678","citing_title":"FedRio: Personalized Federated Social Bot Detection via Cooperative Reinforced Contrastive Adversarial Distillation","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7IT2UGWGV7FILT4RWILFGSC2HS","json":"https://pith.science/pith/7IT2UGWGV7FILT4RWILFGSC2HS.json","graph_json":"https://pith.science/api/pith-number/7IT2UGWGV7FILT4RWILFGSC2HS/graph.json","events_json":"https://pith.science/api/pith-number/7IT2UGWGV7FILT4RWILFGSC2HS/events.json","paper":"https://pith.science/paper/7IT2UGWG"},"agent_actions":{"view_html":"https://pith.science/pith/7IT2UGWGV7FILT4RWILFGSC2HS","download_json":"https://pith.science/pith/7IT2UGWGV7FILT4RWILFGSC2HS.json","view_paper":"https://pith.science/paper/7IT2UGWG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.10619&json=true","fetch_graph":"https://pith.science/api/pith-number/7IT2UGWGV7FILT4RWILFGSC2HS/graph.json","fetch_events":"https://pith.science/api/pith-number/7IT2UGWGV7FILT4RWILFGSC2HS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7IT2UGWGV7FILT4RWILFGSC2HS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7IT2UGWGV7FILT4RWILFGSC2HS/action/storage_attestation","attest_author":"https://pith.science/pith/7IT2UGWGV7FILT4RWILFGSC2HS/action/author_attestation","sign_citation":"https://pith.science/pith/7IT2UGWGV7FILT4RWILFGSC2HS/action/citation_signature","submit_replication":"https://pith.science/pith/7IT2UGWGV7FILT4RWILFGSC2HS/action/replication_record"}},"created_at":"2026-07-05T01:20:15.629549+00:00","updated_at":"2026-07-05T01:20:15.629549+00:00"}