{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:34ZUQMYGJHSNXZQJBWYNYUVRMQ","short_pith_number":"pith:34ZUQMYG","schema_version":"1.0","canonical_sha256":"df3348330649e4dbe6090db0dc52b1642f14ca2fb8269acbbc97ec2d52ba2896","source":{"kind":"arxiv","id":"2207.04338","version":1},"attestation_state":"computed","paper":{"title":"Variance Reduced ProxSkip: Algorithm, Theory and Application to Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","math.OC"],"primary_cat":"cs.LG","authors_text":"Grigory Malinovsky, Kai Yi, Peter Richt\\'arik","submitted_at":"2022-07-09T20:59:30Z","abstract_excerpt":"We study distributed optimization methods based on the {\\em local training (LT)} paradigm: achieving communication efficiency by performing richer local gradient-based training on the clients before parameter averaging. Looking back at the progress of the field, we {\\em identify 5 generations of LT methods}: 1) heuristic, 2) homogeneous, 3) sublinear, 4) linear, and 5) accelerated. The 5${}^{\\rm th}$ generation, initiated by the ProxSkip method of Mishchenko, Malinovsky, Stich and Richt\\'{a}rik (2022) and its analysis, is characterized by the first theoretical confirmation that LT is a communi"},"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":"2207.04338","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-09T20:59:30Z","cross_cats_sorted":["cs.DC","math.OC"],"title_canon_sha256":"482354c7a1c98aee123a551dc94c8036788b240fde9c9529b085f3339e5e7eca","abstract_canon_sha256":"fabfb90b45bc62dd4a19f7a9de4cefffa0014da7a3fd3ea9c649cfea038d1b3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:58.228150Z","signature_b64":"s16tm8QlBaqckd0vnNW/KITacY92zjfW4I4SEBrSTCrHYoZ239ruRxdjF0qUik9j26deowOY30CKMiG4A9hABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df3348330649e4dbe6090db0dc52b1642f14ca2fb8269acbbc97ec2d52ba2896","last_reissued_at":"2026-07-05T04:38:58.227631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:58.227631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variance Reduced ProxSkip: Algorithm, Theory and Application to Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","math.OC"],"primary_cat":"cs.LG","authors_text":"Grigory Malinovsky, Kai Yi, Peter Richt\\'arik","submitted_at":"2022-07-09T20:59:30Z","abstract_excerpt":"We study distributed optimization methods based on the {\\em local training (LT)} paradigm: achieving communication efficiency by performing richer local gradient-based training on the clients before parameter averaging. Looking back at the progress of the field, we {\\em identify 5 generations of LT methods}: 1) heuristic, 2) homogeneous, 3) sublinear, 4) linear, and 5) accelerated. The 5${}^{\\rm th}$ generation, initiated by the ProxSkip method of Mishchenko, Malinovsky, Stich and Richt\\'{a}rik (2022) and its analysis, is characterized by the first theoretical confirmation that LT is a communi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.04338","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/2207.04338/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":"2207.04338","created_at":"2026-07-05T04:38:58.227688+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.04338v1","created_at":"2026-07-05T04:38:58.227688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.04338","created_at":"2026-07-05T04:38:58.227688+00:00"},{"alias_kind":"pith_short_12","alias_value":"34ZUQMYGJHSN","created_at":"2026-07-05T04:38:58.227688+00:00"},{"alias_kind":"pith_short_16","alias_value":"34ZUQMYGJHSNXZQJ","created_at":"2026-07-05T04:38:58.227688+00:00"},{"alias_kind":"pith_short_8","alias_value":"34ZUQMYG","created_at":"2026-07-05T04:38:58.227688+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/34ZUQMYGJHSNXZQJBWYNYUVRMQ","json":"https://pith.science/pith/34ZUQMYGJHSNXZQJBWYNYUVRMQ.json","graph_json":"https://pith.science/api/pith-number/34ZUQMYGJHSNXZQJBWYNYUVRMQ/graph.json","events_json":"https://pith.science/api/pith-number/34ZUQMYGJHSNXZQJBWYNYUVRMQ/events.json","paper":"https://pith.science/paper/34ZUQMYG"},"agent_actions":{"view_html":"https://pith.science/pith/34ZUQMYGJHSNXZQJBWYNYUVRMQ","download_json":"https://pith.science/pith/34ZUQMYGJHSNXZQJBWYNYUVRMQ.json","view_paper":"https://pith.science/paper/34ZUQMYG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.04338&json=true","fetch_graph":"https://pith.science/api/pith-number/34ZUQMYGJHSNXZQJBWYNYUVRMQ/graph.json","fetch_events":"https://pith.science/api/pith-number/34ZUQMYGJHSNXZQJBWYNYUVRMQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/34ZUQMYGJHSNXZQJBWYNYUVRMQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/34ZUQMYGJHSNXZQJBWYNYUVRMQ/action/storage_attestation","attest_author":"https://pith.science/pith/34ZUQMYGJHSNXZQJBWYNYUVRMQ/action/author_attestation","sign_citation":"https://pith.science/pith/34ZUQMYGJHSNXZQJBWYNYUVRMQ/action/citation_signature","submit_replication":"https://pith.science/pith/34ZUQMYGJHSNXZQJBWYNYUVRMQ/action/replication_record"}},"created_at":"2026-07-05T04:38:58.227688+00:00","updated_at":"2026-07-05T04:38:58.227688+00:00"}