{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VZBCGA4GQ3G3MVMTBZDK47AP6D","short_pith_number":"pith:VZBCGA4G","schema_version":"1.0","canonical_sha256":"ae4223038686cdb655930e46ae7c0ff0f52963a01923f8d07fb7bbc326587097","source":{"kind":"arxiv","id":"1802.05811","version":3},"attestation_state":"computed","paper":{"title":"Distributed Stochastic Optimization via Adaptive SGD","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Ashok Cutkosky, Robert Busa-Fekete","submitted_at":"2018-02-16T00:47:00Z","abstract_excerpt":"Stochastic convex optimization algorithms are the most popular way to train machine learning models on large-scale data. Scaling up the training process of these models is crucial, but the most popular algorithm, Stochastic Gradient Descent (SGD), is a serial method that is surprisingly hard to parallelize. In this paper, we propose an efficient distributed stochastic optimization method by combining adaptivity with variance reduction techniques. Our analysis yields a linear speedup in the number of machines, constant memory footprint, and only a logarithmic number of communication rounds. Cri"},"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":"1802.05811","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-16T00:47:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bd061f6eeebbeebfd14eee4e36c7ee6128d2c325f1255e7b13a7c2bbc95b7f8b","abstract_canon_sha256":"f34ae6735802b98304679aa0a82d252af9ec272c7ef1f30a652f05e8c24c967e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:12.887285Z","signature_b64":"M4Jji67fjnWpK6TexMDY/nmZLcDZIToDbJpPuMF/oTmpzpwsVH81OPqoeZOLqwr5zS5ed+sNbut2koL2CQRUBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae4223038686cdb655930e46ae7c0ff0f52963a01923f8d07fb7bbc326587097","last_reissued_at":"2026-05-18T00:02:12.885525Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:12.885525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributed Stochastic Optimization via Adaptive SGD","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Ashok Cutkosky, Robert Busa-Fekete","submitted_at":"2018-02-16T00:47:00Z","abstract_excerpt":"Stochastic convex optimization algorithms are the most popular way to train machine learning models on large-scale data. Scaling up the training process of these models is crucial, but the most popular algorithm, Stochastic Gradient Descent (SGD), is a serial method that is surprisingly hard to parallelize. In this paper, we propose an efficient distributed stochastic optimization method by combining adaptivity with variance reduction techniques. Our analysis yields a linear speedup in the number of machines, constant memory footprint, and only a logarithmic number of communication rounds. Cri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05811","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1802.05811","created_at":"2026-05-18T00:02:12.886598+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.05811v3","created_at":"2026-05-18T00:02:12.886598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05811","created_at":"2026-05-18T00:02:12.886598+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZBCGA4GQ3G3","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZBCGA4GQ3G3MVMT","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZBCGA4G","created_at":"2026-05-18T12:32:59.047623+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/VZBCGA4GQ3G3MVMTBZDK47AP6D","json":"https://pith.science/pith/VZBCGA4GQ3G3MVMTBZDK47AP6D.json","graph_json":"https://pith.science/api/pith-number/VZBCGA4GQ3G3MVMTBZDK47AP6D/graph.json","events_json":"https://pith.science/api/pith-number/VZBCGA4GQ3G3MVMTBZDK47AP6D/events.json","paper":"https://pith.science/paper/VZBCGA4G"},"agent_actions":{"view_html":"https://pith.science/pith/VZBCGA4GQ3G3MVMTBZDK47AP6D","download_json":"https://pith.science/pith/VZBCGA4GQ3G3MVMTBZDK47AP6D.json","view_paper":"https://pith.science/paper/VZBCGA4G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.05811&json=true","fetch_graph":"https://pith.science/api/pith-number/VZBCGA4GQ3G3MVMTBZDK47AP6D/graph.json","fetch_events":"https://pith.science/api/pith-number/VZBCGA4GQ3G3MVMTBZDK47AP6D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZBCGA4GQ3G3MVMTBZDK47AP6D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZBCGA4GQ3G3MVMTBZDK47AP6D/action/storage_attestation","attest_author":"https://pith.science/pith/VZBCGA4GQ3G3MVMTBZDK47AP6D/action/author_attestation","sign_citation":"https://pith.science/pith/VZBCGA4GQ3G3MVMTBZDK47AP6D/action/citation_signature","submit_replication":"https://pith.science/pith/VZBCGA4GQ3G3MVMTBZDK47AP6D/action/replication_record"}},"created_at":"2026-05-18T00:02:12.886598+00:00","updated_at":"2026-05-18T00:02:12.886598+00:00"}