{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:BLI5YJSVSCJUXEMOX7X2H4633U","short_pith_number":"pith:BLI5YJSV","schema_version":"1.0","canonical_sha256":"0ad1dc265590934b918ebfefa3f3dbdd11c927d77ee9aced92c546196e5ab6a4","source":{"kind":"arxiv","id":"1506.06840","version":2},"attestation_state":"computed","paper":{"title":"On Variance Reduction in Stochastic Gradient Descent and its Asynchronous Variants","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ahmed Hefny, Alex Smola, Barnab\\'as P\\'oczos, Sashank J. Reddi, Suvrit Sra","submitted_at":"2015-06-23T01:57:19Z","abstract_excerpt":"We study optimization algorithms based on variance reduction for stochastic gradient descent (SGD). Remarkable recent progress has been made in this direction through development of algorithms like SAG, SVRG, SAGA. These algorithms have been shown to outperform SGD, both theoretically and empirically. However, asynchronous versions of these algorithms---a crucial requirement for modern large-scale applications---have not been studied. We bridge this gap by presenting a unifying framework for many variance reduction techniques. Subsequently, we propose an asynchronous algorithm grounded in our "},"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":"1506.06840","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-23T01:57:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ae98ef76aa69040435b4f237661951e7b9424324ccd3a9597562824d0ebf4cc2","abstract_canon_sha256":"63380360579ccbff8d13402a79304af81af042f449824f036fbcbfe10ca3d88e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:22:07.878541Z","signature_b64":"5lmbqLBtJQta9A3kaXwjEL4hF6gZ3UvdqY+pn1sE+od2pOU7xqRFc7InMX0ADYc7Dd8xGogHntY+/UiP2XL2CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ad1dc265590934b918ebfefa3f3dbdd11c927d77ee9aced92c546196e5ab6a4","last_reissued_at":"2026-05-18T01:22:07.877995Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:22:07.877995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Variance Reduction in Stochastic Gradient Descent and its Asynchronous Variants","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ahmed Hefny, Alex Smola, Barnab\\'as P\\'oczos, Sashank J. Reddi, Suvrit Sra","submitted_at":"2015-06-23T01:57:19Z","abstract_excerpt":"We study optimization algorithms based on variance reduction for stochastic gradient descent (SGD). Remarkable recent progress has been made in this direction through development of algorithms like SAG, SVRG, SAGA. These algorithms have been shown to outperform SGD, both theoretically and empirically. However, asynchronous versions of these algorithms---a crucial requirement for modern large-scale applications---have not been studied. We bridge this gap by presenting a unifying framework for many variance reduction techniques. Subsequently, we propose an asynchronous algorithm grounded in our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.06840","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":""},"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":"1506.06840","created_at":"2026-05-18T01:22:07.878082+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.06840v2","created_at":"2026-05-18T01:22:07.878082+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.06840","created_at":"2026-05-18T01:22:07.878082+00:00"},{"alias_kind":"pith_short_12","alias_value":"BLI5YJSVSCJU","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_16","alias_value":"BLI5YJSVSCJUXEMO","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_8","alias_value":"BLI5YJSV","created_at":"2026-05-18T12:29:14.074870+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/BLI5YJSVSCJUXEMOX7X2H4633U","json":"https://pith.science/pith/BLI5YJSVSCJUXEMOX7X2H4633U.json","graph_json":"https://pith.science/api/pith-number/BLI5YJSVSCJUXEMOX7X2H4633U/graph.json","events_json":"https://pith.science/api/pith-number/BLI5YJSVSCJUXEMOX7X2H4633U/events.json","paper":"https://pith.science/paper/BLI5YJSV"},"agent_actions":{"view_html":"https://pith.science/pith/BLI5YJSVSCJUXEMOX7X2H4633U","download_json":"https://pith.science/pith/BLI5YJSVSCJUXEMOX7X2H4633U.json","view_paper":"https://pith.science/paper/BLI5YJSV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.06840&json=true","fetch_graph":"https://pith.science/api/pith-number/BLI5YJSVSCJUXEMOX7X2H4633U/graph.json","fetch_events":"https://pith.science/api/pith-number/BLI5YJSVSCJUXEMOX7X2H4633U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BLI5YJSVSCJUXEMOX7X2H4633U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BLI5YJSVSCJUXEMOX7X2H4633U/action/storage_attestation","attest_author":"https://pith.science/pith/BLI5YJSVSCJUXEMOX7X2H4633U/action/author_attestation","sign_citation":"https://pith.science/pith/BLI5YJSVSCJUXEMOX7X2H4633U/action/citation_signature","submit_replication":"https://pith.science/pith/BLI5YJSVSCJUXEMOX7X2H4633U/action/replication_record"}},"created_at":"2026-05-18T01:22:07.878082+00:00","updated_at":"2026-05-18T01:22:07.878082+00:00"}