{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TSN4BDHH7GR4W3XBWJBKQMARSS","short_pith_number":"pith:TSN4BDHH","schema_version":"1.0","canonical_sha256":"9c9bc08ce7f9a3cb6ee1b242a830119498e5c12043aad1a9c0af136ba16ca280","source":{"kind":"arxiv","id":"1808.03880","version":2},"attestation_state":"computed","paper":{"title":"Parallelization does not Accelerate Convex Optimization: Adaptivity Lower Bounds for Non-smooth Convex Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.DS","cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eric Balkanski, Yaron Singer","submitted_at":"2018-08-12T01:56:17Z","abstract_excerpt":"In this paper we study the limitations of parallelization in convex optimization. A convenient approach to study parallelization is through the prism of \\emph{adaptivity} which is an information theoretic measure of the parallel runtime of an algorithm [BS18]. Informally, adaptivity is the number of sequential rounds an algorithm needs to make when it can execute polynomially-many queries in parallel at every round. For combinatorial optimization with black-box oracle access, the study of adaptivity has recently led to exponential accelerations in parallel runtime and the natural question is w"},"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":"1808.03880","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-12T01:56:17Z","cross_cats_sorted":["cs.DC","cs.DS","cs.IT","math.IT","stat.ML"],"title_canon_sha256":"570b0131b580e926d38bd711946c50ed82832418d0263f8290f0d3fd89d8987e","abstract_canon_sha256":"45a25a638584447b5b6f2d7391d638278de00666ce61982b585347239d1f15d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:20:50.667015Z","signature_b64":"Pk2ZsjhdJZ7mQJCAW6y+ZxLvS6YIiplQXznc3/ieChsiUd1Uxn5VKEhgDjcwK5judsicjOIRi0SvpTQbVwv0AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c9bc08ce7f9a3cb6ee1b242a830119498e5c12043aad1a9c0af136ba16ca280","last_reissued_at":"2026-07-05T00:20:50.666626Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:20:50.666626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parallelization does not Accelerate Convex Optimization: Adaptivity Lower Bounds for Non-smooth Convex Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.DS","cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eric Balkanski, Yaron Singer","submitted_at":"2018-08-12T01:56:17Z","abstract_excerpt":"In this paper we study the limitations of parallelization in convex optimization. A convenient approach to study parallelization is through the prism of \\emph{adaptivity} which is an information theoretic measure of the parallel runtime of an algorithm [BS18]. Informally, adaptivity is the number of sequential rounds an algorithm needs to make when it can execute polynomially-many queries in parallel at every round. For combinatorial optimization with black-box oracle access, the study of adaptivity has recently led to exponential accelerations in parallel runtime and the natural question is w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.03880","kind":"arxiv","version":2},"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/1808.03880/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":"1808.03880","created_at":"2026-07-05T00:20:50.666680+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.03880v2","created_at":"2026-07-05T00:20:50.666680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.03880","created_at":"2026-07-05T00:20:50.666680+00:00"},{"alias_kind":"pith_short_12","alias_value":"TSN4BDHH7GR4","created_at":"2026-07-05T00:20:50.666680+00:00"},{"alias_kind":"pith_short_16","alias_value":"TSN4BDHH7GR4W3XB","created_at":"2026-07-05T00:20:50.666680+00:00"},{"alias_kind":"pith_short_8","alias_value":"TSN4BDHH","created_at":"2026-07-05T00:20:50.666680+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.17082","citing_title":"MARINA-P: Superior Performance in Non-smooth Federated Optimization with Adaptive Stepsizes","ref_index":2015,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TSN4BDHH7GR4W3XBWJBKQMARSS","json":"https://pith.science/pith/TSN4BDHH7GR4W3XBWJBKQMARSS.json","graph_json":"https://pith.science/api/pith-number/TSN4BDHH7GR4W3XBWJBKQMARSS/graph.json","events_json":"https://pith.science/api/pith-number/TSN4BDHH7GR4W3XBWJBKQMARSS/events.json","paper":"https://pith.science/paper/TSN4BDHH"},"agent_actions":{"view_html":"https://pith.science/pith/TSN4BDHH7GR4W3XBWJBKQMARSS","download_json":"https://pith.science/pith/TSN4BDHH7GR4W3XBWJBKQMARSS.json","view_paper":"https://pith.science/paper/TSN4BDHH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.03880&json=true","fetch_graph":"https://pith.science/api/pith-number/TSN4BDHH7GR4W3XBWJBKQMARSS/graph.json","fetch_events":"https://pith.science/api/pith-number/TSN4BDHH7GR4W3XBWJBKQMARSS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TSN4BDHH7GR4W3XBWJBKQMARSS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TSN4BDHH7GR4W3XBWJBKQMARSS/action/storage_attestation","attest_author":"https://pith.science/pith/TSN4BDHH7GR4W3XBWJBKQMARSS/action/author_attestation","sign_citation":"https://pith.science/pith/TSN4BDHH7GR4W3XBWJBKQMARSS/action/citation_signature","submit_replication":"https://pith.science/pith/TSN4BDHH7GR4W3XBWJBKQMARSS/action/replication_record"}},"created_at":"2026-07-05T00:20:50.666680+00:00","updated_at":"2026-07-05T00:20:50.666680+00:00"}