{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZKQVK3E4XOXAUYJXLSMBXUYGNR","short_pith_number":"pith:ZKQVK3E4","schema_version":"1.0","canonical_sha256":"caa1556c9cbbae0a61375c981bd3066c7227e532a947d8c6e2221c0601eb3e6b","source":{"kind":"arxiv","id":"2507.23725","version":1},"attestation_state":"computed","paper":{"title":"Adaptive Stepsize Selection in Decentralized Convex Optimization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Alexander Gasnikov, Gesualdo Scutari, Ilya Kuruzov, Xiaokai Chen","submitted_at":"2025-07-31T16:58:40Z","abstract_excerpt":"We study decentralized optimization where multiple agents minimize the average of their (strongly) convex, smooth losses over a communication graph. Convergence of the existing decentralized methods generally hinges on an apriori, proper selection of the stepsize. Choosing this value is notoriously delicate: (i) it demands global knowledge from all the agents of the graph's connectivity and every local smoothness/strong-convexity constants--information they rarely have; (ii) even with perfect information, the worst-case tuning forces an overly small stepsize, slowing convergence in practice; a"},"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":"2507.23725","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"math.OC","submitted_at":"2025-07-31T16:58:40Z","cross_cats_sorted":[],"title_canon_sha256":"560a7b154a90d628f87c32c04925537efe8313d5bc1c29e152ac5e7bb366c22e","abstract_canon_sha256":"204885d58d65fa2b0f818a39f2522d8d94935ca2a2312fffe7351e69e5aa70da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:30.073814Z","signature_b64":"2zxLospvVGx5orU5BtbFK7ZVoUljTJwD83iNzgxqSFfi3g5AxxzZMNV+Dh+P5Y/L8GCwKqAwwzbgJrIbS0bODw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"caa1556c9cbbae0a61375c981bd3066c7227e532a947d8c6e2221c0601eb3e6b","last_reissued_at":"2026-07-05T11:46:30.073273Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:30.073273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Stepsize Selection in Decentralized Convex Optimization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Alexander Gasnikov, Gesualdo Scutari, Ilya Kuruzov, Xiaokai Chen","submitted_at":"2025-07-31T16:58:40Z","abstract_excerpt":"We study decentralized optimization where multiple agents minimize the average of their (strongly) convex, smooth losses over a communication graph. Convergence of the existing decentralized methods generally hinges on an apriori, proper selection of the stepsize. Choosing this value is notoriously delicate: (i) it demands global knowledge from all the agents of the graph's connectivity and every local smoothness/strong-convexity constants--information they rarely have; (ii) even with perfect information, the worst-case tuning forces an overly small stepsize, slowing convergence in practice; a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23725","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/2507.23725/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":"2507.23725","created_at":"2026-07-05T11:46:30.073341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.23725v1","created_at":"2026-07-05T11:46:30.073341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23725","created_at":"2026-07-05T11:46:30.073341+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKQVK3E4XOXA","created_at":"2026-07-05T11:46:30.073341+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKQVK3E4XOXAUYJX","created_at":"2026-07-05T11:46:30.073341+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKQVK3E4","created_at":"2026-07-05T11:46:30.073341+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00711","citing_title":"A Line-search-free Method for Adaptive Decentralized Optimization","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZKQVK3E4XOXAUYJXLSMBXUYGNR","json":"https://pith.science/pith/ZKQVK3E4XOXAUYJXLSMBXUYGNR.json","graph_json":"https://pith.science/api/pith-number/ZKQVK3E4XOXAUYJXLSMBXUYGNR/graph.json","events_json":"https://pith.science/api/pith-number/ZKQVK3E4XOXAUYJXLSMBXUYGNR/events.json","paper":"https://pith.science/paper/ZKQVK3E4"},"agent_actions":{"view_html":"https://pith.science/pith/ZKQVK3E4XOXAUYJXLSMBXUYGNR","download_json":"https://pith.science/pith/ZKQVK3E4XOXAUYJXLSMBXUYGNR.json","view_paper":"https://pith.science/paper/ZKQVK3E4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.23725&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKQVK3E4XOXAUYJXLSMBXUYGNR/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKQVK3E4XOXAUYJXLSMBXUYGNR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKQVK3E4XOXAUYJXLSMBXUYGNR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKQVK3E4XOXAUYJXLSMBXUYGNR/action/storage_attestation","attest_author":"https://pith.science/pith/ZKQVK3E4XOXAUYJXLSMBXUYGNR/action/author_attestation","sign_citation":"https://pith.science/pith/ZKQVK3E4XOXAUYJXLSMBXUYGNR/action/citation_signature","submit_replication":"https://pith.science/pith/ZKQVK3E4XOXAUYJXLSMBXUYGNR/action/replication_record"}},"created_at":"2026-07-05T11:46:30.073341+00:00","updated_at":"2026-07-05T11:46:30.073341+00:00"}