{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HUITCSJYJN63SRDQ6ERTQQDKXW","short_pith_number":"pith:HUITCSJY","schema_version":"1.0","canonical_sha256":"3d113149384b7db94470f12338406abd9f8b6b3adacc05c72b012c9dfff552c5","source":{"kind":"arxiv","id":"2205.15136","version":1},"attestation_state":"computed","paper":{"title":"Optimal Gradient Sliding and its Application to Distributed Optimization Under Similarity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.LG"],"primary_cat":"math.OC","authors_text":"Aleksandr Beznosikov, Alexander Gasnikov, Dmitry Kovalev, Ekaterina Borodich, Gesualdo Scutari","submitted_at":"2022-05-30T14:28:02Z","abstract_excerpt":"We study structured convex optimization problems, with additive objective $r:=p + q$, where $r$ is ($\\mu$-strongly) convex, $q$ is $L_q$-smooth and convex, and $p$ is $L_p$-smooth, possibly nonconvex. For such a class of problems, we proposed an inexact accelerated gradient sliding method that can skip the gradient computation for one of these components while still achieving optimal complexity of gradient calls of $p$ and $q$, that is,\n  $\\mathcal{O}(\\sqrt{L_p/\\mu})$ and $\\mathcal{O}(\\sqrt{L_q/\\mu})$, respectively. This result is much sharper than the classic black-box complexity $\\mathcal{O}"},"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":"2205.15136","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-05-30T14:28:02Z","cross_cats_sorted":["cs.DC","cs.LG"],"title_canon_sha256":"7fa6bf9cf4133a699daa84a0e8300b0326a9b60cdd5e0746a32d79e5f82963a8","abstract_canon_sha256":"2b98679cce7823ffb4b0d9b9024c04364b60b499d311984b06165071644d250a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:24.913661Z","signature_b64":"uWa2qZfTgWMNHd9zI8axJOYu4wDP7/6cDuEw1TbcpraxlgmMaNauL0xwcDDNpkDSQ+vsrVt9IAvgyG7uAOwaCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d113149384b7db94470f12338406abd9f8b6b3adacc05c72b012c9dfff552c5","last_reissued_at":"2026-07-05T04:27:24.913242Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:24.913242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Gradient Sliding and its Application to Distributed Optimization Under Similarity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.LG"],"primary_cat":"math.OC","authors_text":"Aleksandr Beznosikov, Alexander Gasnikov, Dmitry Kovalev, Ekaterina Borodich, Gesualdo Scutari","submitted_at":"2022-05-30T14:28:02Z","abstract_excerpt":"We study structured convex optimization problems, with additive objective $r:=p + q$, where $r$ is ($\\mu$-strongly) convex, $q$ is $L_q$-smooth and convex, and $p$ is $L_p$-smooth, possibly nonconvex. For such a class of problems, we proposed an inexact accelerated gradient sliding method that can skip the gradient computation for one of these components while still achieving optimal complexity of gradient calls of $p$ and $q$, that is,\n  $\\mathcal{O}(\\sqrt{L_p/\\mu})$ and $\\mathcal{O}(\\sqrt{L_q/\\mu})$, respectively. This result is much sharper than the classic black-box complexity $\\mathcal{O}"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15136","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/2205.15136/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":"2205.15136","created_at":"2026-07-05T04:27:24.913301+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.15136v1","created_at":"2026-07-05T04:27:24.913301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15136","created_at":"2026-07-05T04:27:24.913301+00:00"},{"alias_kind":"pith_short_12","alias_value":"HUITCSJYJN63","created_at":"2026-07-05T04:27:24.913301+00:00"},{"alias_kind":"pith_short_16","alias_value":"HUITCSJYJN63SRDQ","created_at":"2026-07-05T04:27:24.913301+00:00"},{"alias_kind":"pith_short_8","alias_value":"HUITCSJY","created_at":"2026-07-05T04:27:24.913301+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.15832","citing_title":"SILAGE: Memory-Efficient, Full-Gradient-Free Nonconvex Optimization for Nested Finite Sums","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16875","citing_title":"Stochastic Optimization and Data Science","ref_index":112,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13434","citing_title":"Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HUITCSJYJN63SRDQ6ERTQQDKXW","json":"https://pith.science/pith/HUITCSJYJN63SRDQ6ERTQQDKXW.json","graph_json":"https://pith.science/api/pith-number/HUITCSJYJN63SRDQ6ERTQQDKXW/graph.json","events_json":"https://pith.science/api/pith-number/HUITCSJYJN63SRDQ6ERTQQDKXW/events.json","paper":"https://pith.science/paper/HUITCSJY"},"agent_actions":{"view_html":"https://pith.science/pith/HUITCSJYJN63SRDQ6ERTQQDKXW","download_json":"https://pith.science/pith/HUITCSJYJN63SRDQ6ERTQQDKXW.json","view_paper":"https://pith.science/paper/HUITCSJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.15136&json=true","fetch_graph":"https://pith.science/api/pith-number/HUITCSJYJN63SRDQ6ERTQQDKXW/graph.json","fetch_events":"https://pith.science/api/pith-number/HUITCSJYJN63SRDQ6ERTQQDKXW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HUITCSJYJN63SRDQ6ERTQQDKXW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HUITCSJYJN63SRDQ6ERTQQDKXW/action/storage_attestation","attest_author":"https://pith.science/pith/HUITCSJYJN63SRDQ6ERTQQDKXW/action/author_attestation","sign_citation":"https://pith.science/pith/HUITCSJYJN63SRDQ6ERTQQDKXW/action/citation_signature","submit_replication":"https://pith.science/pith/HUITCSJYJN63SRDQ6ERTQQDKXW/action/replication_record"}},"created_at":"2026-07-05T04:27:24.913301+00:00","updated_at":"2026-07-05T04:27:24.913301+00:00"}