{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QDFQFYIQD6JRBVLL2WBCOZWSKQ","short_pith_number":"pith:QDFQFYIQ","schema_version":"1.0","canonical_sha256":"80cb02e1101f9310d56bd5822766d2543dc850fed4282eabd1057eb2c2364b85","source":{"kind":"arxiv","id":"2102.12660","version":1},"attestation_state":"computed","paper":{"title":"Distributionally Robust Federated Averaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mehrdad Mahdavi, Mohammad Mahdi Kamani, Yuyang Deng","submitted_at":"2021-02-25T03:32:09Z","abstract_excerpt":"In this paper, we study communication efficient distributed algorithms for distributionally robust federated learning via periodic averaging with adaptive sampling. In contrast to standard empirical risk minimization, due to the minimax structure of the underlying optimization problem, a key difficulty arises from the fact that the global parameter that controls the mixture of local losses can only be updated infrequently on the global stage. To compensate for this, we propose a Distributionally Robust Federated Averaging (DRFA) algorithm that employs a novel snapshotting scheme to approximate"},"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":"2102.12660","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-25T03:32:09Z","cross_cats_sorted":["cs.DC","stat.ML"],"title_canon_sha256":"898b9c7c0c75b72f8c644d085fb3d89a731114cfdf400ac234d70a4a343d7b85","abstract_canon_sha256":"3a8b949debef60137bdc407125bdfe407ac6c81cc573e75debdd6ce6016d4602"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:18:22.628896Z","signature_b64":"IzHil06GnVaNG8hJN5buFaAGcO56UwBbfu2bcdGgnEf6eSU+b/ds6O82uBL5Msg6ne6+4BZ68UOi+O057qJfCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80cb02e1101f9310d56bd5822766d2543dc850fed4282eabd1057eb2c2364b85","last_reissued_at":"2026-07-05T02:18:22.628539Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:18:22.628539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributionally Robust Federated Averaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mehrdad Mahdavi, Mohammad Mahdi Kamani, Yuyang Deng","submitted_at":"2021-02-25T03:32:09Z","abstract_excerpt":"In this paper, we study communication efficient distributed algorithms for distributionally robust federated learning via periodic averaging with adaptive sampling. In contrast to standard empirical risk minimization, due to the minimax structure of the underlying optimization problem, a key difficulty arises from the fact that the global parameter that controls the mixture of local losses can only be updated infrequently on the global stage. To compensate for this, we propose a Distributionally Robust Federated Averaging (DRFA) algorithm that employs a novel snapshotting scheme to approximate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.12660","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/2102.12660/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":"2102.12660","created_at":"2026-07-05T02:18:22.628604+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.12660v1","created_at":"2026-07-05T02:18:22.628604+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.12660","created_at":"2026-07-05T02:18:22.628604+00:00"},{"alias_kind":"pith_short_12","alias_value":"QDFQFYIQD6JR","created_at":"2026-07-05T02:18:22.628604+00:00"},{"alias_kind":"pith_short_16","alias_value":"QDFQFYIQD6JRBVLL","created_at":"2026-07-05T02:18:22.628604+00:00"},{"alias_kind":"pith_short_8","alias_value":"QDFQFYIQ","created_at":"2026-07-05T02:18:22.628604+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.15371","citing_title":"Distributionally Robust Federated Learning with Client Drift Minimization","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QDFQFYIQD6JRBVLL2WBCOZWSKQ","json":"https://pith.science/pith/QDFQFYIQD6JRBVLL2WBCOZWSKQ.json","graph_json":"https://pith.science/api/pith-number/QDFQFYIQD6JRBVLL2WBCOZWSKQ/graph.json","events_json":"https://pith.science/api/pith-number/QDFQFYIQD6JRBVLL2WBCOZWSKQ/events.json","paper":"https://pith.science/paper/QDFQFYIQ"},"agent_actions":{"view_html":"https://pith.science/pith/QDFQFYIQD6JRBVLL2WBCOZWSKQ","download_json":"https://pith.science/pith/QDFQFYIQD6JRBVLL2WBCOZWSKQ.json","view_paper":"https://pith.science/paper/QDFQFYIQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.12660&json=true","fetch_graph":"https://pith.science/api/pith-number/QDFQFYIQD6JRBVLL2WBCOZWSKQ/graph.json","fetch_events":"https://pith.science/api/pith-number/QDFQFYIQD6JRBVLL2WBCOZWSKQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QDFQFYIQD6JRBVLL2WBCOZWSKQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QDFQFYIQD6JRBVLL2WBCOZWSKQ/action/storage_attestation","attest_author":"https://pith.science/pith/QDFQFYIQD6JRBVLL2WBCOZWSKQ/action/author_attestation","sign_citation":"https://pith.science/pith/QDFQFYIQD6JRBVLL2WBCOZWSKQ/action/citation_signature","submit_replication":"https://pith.science/pith/QDFQFYIQD6JRBVLL2WBCOZWSKQ/action/replication_record"}},"created_at":"2026-07-05T02:18:22.628604+00:00","updated_at":"2026-07-05T02:18:22.628604+00:00"}