{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:7HEK5QPMNTP22DT4YVPDW5ZLFJ","short_pith_number":"pith:7HEK5QPM","schema_version":"1.0","canonical_sha256":"f9c8aec1ec6cdfad0e7cc55e3b772b2a4a2df1b87e9255aa104fa97107021607","source":{"kind":"arxiv","id":"1506.03662","version":4},"attestation_state":"computed","paper":{"title":"Variance Reduced Stochastic Gradient Descent with Neighbors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aurelien Lucchi, Brian McWilliams, Simon Lacoste-Julien, Thomas Hofmann","submitted_at":"2015-06-11T13:14:33Z","abstract_excerpt":"Stochastic Gradient Descent (SGD) is a workhorse in machine learning, yet its slow convergence can be a computational bottleneck. Variance reduction techniques such as SAG, SVRG and SAGA have been proposed to overcome this weakness, achieving linear convergence. However, these methods are either based on computations of full gradients at pivot points, or on keeping per data point corrections in memory. Therefore speed-ups relative to SGD may need a minimal number of epochs in order to materialize. This paper investigates algorithms that can exploit neighborhood structure in the training data t"},"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":"1506.03662","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-11T13:14:33Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"c89db80ce502fc0c8bc3d13f7280c5315bbf205b47ebe3eeacbe54227d4d0a53","abstract_canon_sha256":"09908aef5c1013326a3e54b2250be967a03c8dbb35429c5661c3226a12d77726"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:19:57.396130Z","signature_b64":"MQEVVmAiGpPZFqghE02h9kH4eEAgLo526TX3WiO9os6WohOz0vi0QjqCRF/kXSMJ/tXTeLQPNC4IzaYgBXcrDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9c8aec1ec6cdfad0e7cc55e3b772b2a4a2df1b87e9255aa104fa97107021607","last_reissued_at":"2026-05-18T01:19:57.395461Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:19:57.395461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variance Reduced Stochastic Gradient Descent with Neighbors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aurelien Lucchi, Brian McWilliams, Simon Lacoste-Julien, Thomas Hofmann","submitted_at":"2015-06-11T13:14:33Z","abstract_excerpt":"Stochastic Gradient Descent (SGD) is a workhorse in machine learning, yet its slow convergence can be a computational bottleneck. Variance reduction techniques such as SAG, SVRG and SAGA have been proposed to overcome this weakness, achieving linear convergence. However, these methods are either based on computations of full gradients at pivot points, or on keeping per data point corrections in memory. Therefore speed-ups relative to SGD may need a minimal number of epochs in order to materialize. This paper investigates algorithms that can exploit neighborhood structure in the training data t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.03662","kind":"arxiv","version":4},"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":"1506.03662","created_at":"2026-05-18T01:19:57.395557+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.03662v4","created_at":"2026-05-18T01:19:57.395557+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.03662","created_at":"2026-05-18T01:19:57.395557+00:00"},{"alias_kind":"pith_short_12","alias_value":"7HEK5QPMNTP2","created_at":"2026-05-18T12:29:10.953037+00:00"},{"alias_kind":"pith_short_16","alias_value":"7HEK5QPMNTP22DT4","created_at":"2026-05-18T12:29:10.953037+00:00"},{"alias_kind":"pith_short_8","alias_value":"7HEK5QPM","created_at":"2026-05-18T12:29:10.953037+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/7HEK5QPMNTP22DT4YVPDW5ZLFJ","json":"https://pith.science/pith/7HEK5QPMNTP22DT4YVPDW5ZLFJ.json","graph_json":"https://pith.science/api/pith-number/7HEK5QPMNTP22DT4YVPDW5ZLFJ/graph.json","events_json":"https://pith.science/api/pith-number/7HEK5QPMNTP22DT4YVPDW5ZLFJ/events.json","paper":"https://pith.science/paper/7HEK5QPM"},"agent_actions":{"view_html":"https://pith.science/pith/7HEK5QPMNTP22DT4YVPDW5ZLFJ","download_json":"https://pith.science/pith/7HEK5QPMNTP22DT4YVPDW5ZLFJ.json","view_paper":"https://pith.science/paper/7HEK5QPM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.03662&json=true","fetch_graph":"https://pith.science/api/pith-number/7HEK5QPMNTP22DT4YVPDW5ZLFJ/graph.json","fetch_events":"https://pith.science/api/pith-number/7HEK5QPMNTP22DT4YVPDW5ZLFJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7HEK5QPMNTP22DT4YVPDW5ZLFJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7HEK5QPMNTP22DT4YVPDW5ZLFJ/action/storage_attestation","attest_author":"https://pith.science/pith/7HEK5QPMNTP22DT4YVPDW5ZLFJ/action/author_attestation","sign_citation":"https://pith.science/pith/7HEK5QPMNTP22DT4YVPDW5ZLFJ/action/citation_signature","submit_replication":"https://pith.science/pith/7HEK5QPMNTP22DT4YVPDW5ZLFJ/action/replication_record"}},"created_at":"2026-05-18T01:19:57.395557+00:00","updated_at":"2026-05-18T01:19:57.395557+00:00"}