{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SS72YVRIAEFLG7ZKHBKQDJT63G","short_pith_number":"pith:SS72YVRI","schema_version":"1.0","canonical_sha256":"94bfac5628010ab37f2a385501a67ed98f7ce5b1cfebddd6af45fb54195bb28d","source":{"kind":"arxiv","id":"2507.17534","version":1},"attestation_state":"computed","paper":{"title":"Federated Majorize-Minimization: Beyond Parameter Aggregation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aymeric Dieuleveut, Gersende Fort, Hoi-To Wai, Mahmoud Hegazy","submitted_at":"2025-07-23T14:13:19Z","abstract_excerpt":"This paper proposes a unified approach for designing stochastic optimization algorithms that robustly scale to the federated learning setting. Our work studies a class of Majorize-Minimization (MM) problems, which possesses a linearly parameterized family of majorizing surrogate functions. This framework encompasses (proximal) gradient-based algorithms for (regularized) smooth objectives, the Expectation Maximization algorithm, and many problems seen as variational surrogate MM. We show that our framework motivates a unifying algorithm called Stochastic Approximation Stochastic Surrogate MM (\\"},"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":"2507.17534","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-23T14:13:19Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"15fb72d2450664278ef30acdcc1217c965a20e19139685d516384c7df8f2cef6","abstract_canon_sha256":"d95bf431a56e1da749c3c1f557a2e546eb4c0e1f25319042dc29e3aba543e595"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:09.584705Z","signature_b64":"Qe14LG7ZOTh07/9giVFlbB58kJ4W901enhc+0zpVmyY4wJ+JRB0ivIhMiav57ofLydDNPS0O19mO+P10cs5gBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94bfac5628010ab37f2a385501a67ed98f7ce5b1cfebddd6af45fb54195bb28d","last_reissued_at":"2026-07-05T11:42:09.584227Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:09.584227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Majorize-Minimization: Beyond Parameter Aggregation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aymeric Dieuleveut, Gersende Fort, Hoi-To Wai, Mahmoud Hegazy","submitted_at":"2025-07-23T14:13:19Z","abstract_excerpt":"This paper proposes a unified approach for designing stochastic optimization algorithms that robustly scale to the federated learning setting. Our work studies a class of Majorize-Minimization (MM) problems, which possesses a linearly parameterized family of majorizing surrogate functions. This framework encompasses (proximal) gradient-based algorithms for (regularized) smooth objectives, the Expectation Maximization algorithm, and many problems seen as variational surrogate MM. We show that our framework motivates a unifying algorithm called Stochastic Approximation Stochastic Surrogate MM (\\"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17534","kind":"arxiv","version":1},"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/2507.17534/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":"2507.17534","created_at":"2026-07-05T11:42:09.584288+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.17534v1","created_at":"2026-07-05T11:42:09.584288+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17534","created_at":"2026-07-05T11:42:09.584288+00:00"},{"alias_kind":"pith_short_12","alias_value":"SS72YVRIAEFL","created_at":"2026-07-05T11:42:09.584288+00:00"},{"alias_kind":"pith_short_16","alias_value":"SS72YVRIAEFLG7ZK","created_at":"2026-07-05T11:42:09.584288+00:00"},{"alias_kind":"pith_short_8","alias_value":"SS72YVRI","created_at":"2026-07-05T11:42:09.584288+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/SS72YVRIAEFLG7ZKHBKQDJT63G","json":"https://pith.science/pith/SS72YVRIAEFLG7ZKHBKQDJT63G.json","graph_json":"https://pith.science/api/pith-number/SS72YVRIAEFLG7ZKHBKQDJT63G/graph.json","events_json":"https://pith.science/api/pith-number/SS72YVRIAEFLG7ZKHBKQDJT63G/events.json","paper":"https://pith.science/paper/SS72YVRI"},"agent_actions":{"view_html":"https://pith.science/pith/SS72YVRIAEFLG7ZKHBKQDJT63G","download_json":"https://pith.science/pith/SS72YVRIAEFLG7ZKHBKQDJT63G.json","view_paper":"https://pith.science/paper/SS72YVRI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.17534&json=true","fetch_graph":"https://pith.science/api/pith-number/SS72YVRIAEFLG7ZKHBKQDJT63G/graph.json","fetch_events":"https://pith.science/api/pith-number/SS72YVRIAEFLG7ZKHBKQDJT63G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SS72YVRIAEFLG7ZKHBKQDJT63G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SS72YVRIAEFLG7ZKHBKQDJT63G/action/storage_attestation","attest_author":"https://pith.science/pith/SS72YVRIAEFLG7ZKHBKQDJT63G/action/author_attestation","sign_citation":"https://pith.science/pith/SS72YVRIAEFLG7ZKHBKQDJT63G/action/citation_signature","submit_replication":"https://pith.science/pith/SS72YVRIAEFLG7ZKHBKQDJT63G/action/replication_record"}},"created_at":"2026-07-05T11:42:09.584288+00:00","updated_at":"2026-07-05T11:42:09.584288+00:00"}