{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZBCOYK3LZCSX2WDPMA4AOGMWMJ","short_pith_number":"pith:ZBCOYK3L","schema_version":"1.0","canonical_sha256":"c844ec2b6bc8a57d586f6038071996627cd107573a894c680021065c71792abe","source":{"kind":"arxiv","id":"2605.19291","version":1},"attestation_state":"computed","paper":{"title":"Factor Augmented High-Dimensional SGD","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Shubo Li, Xiufan Yu, Yuefeng Han","submitted_at":"2026-05-19T03:10:33Z","abstract_excerpt":"Stochastic gradient descent (SGD) is a fundamental optimization algorithm widely used in modern machine learning. In this paper, we propose Factor-Augmented SGD (FSGD), a new optimization method that leverages latent factor representations in high-dimensional learning tasks. Unlike standard two-stage dimension reduction approaches that rely on offline representation learning and full data storage, a key novelty of FSGD is that it operates purely on streaming data, making it scalable to large-scale and high-dimensional problems. Furthermore, we establish the first theoretical framework that exp"},"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":"2605.19291","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-19T03:10:33Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"893d09d17807336454214b6c25b2fbc9cce591d9f2b319c7645e76cebd732053","abstract_canon_sha256":"44bb379378ee3da0d2077002f7aafeab38361c0d54457c3d185d83442a0773c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:37.907688Z","signature_b64":"jl2Yg+LGBveCPPBFabXr/z1uG+qHtFLBLzKY4V60KtGJKCmK/z1fgCO8rBy3egwVJIjhkCVD9iIomRwBt7MJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c844ec2b6bc8a57d586f6038071996627cd107573a894c680021065c71792abe","last_reissued_at":"2026-05-20T01:05:37.906820Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:37.906820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Factor Augmented High-Dimensional SGD","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Shubo Li, Xiufan Yu, Yuefeng Han","submitted_at":"2026-05-19T03:10:33Z","abstract_excerpt":"Stochastic gradient descent (SGD) is a fundamental optimization algorithm widely used in modern machine learning. In this paper, we propose Factor-Augmented SGD (FSGD), a new optimization method that leverages latent factor representations in high-dimensional learning tasks. Unlike standard two-stage dimension reduction approaches that rely on offline representation learning and full data storage, a key novelty of FSGD is that it operates purely on streaming data, making it scalable to large-scale and high-dimensional problems. Furthermore, we establish the first theoretical framework that exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19291","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/2605.19291/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":"2605.19291","created_at":"2026-05-20T01:05:37.906964+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.19291v1","created_at":"2026-05-20T01:05:37.906964+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19291","created_at":"2026-05-20T01:05:37.906964+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZBCOYK3LZCSX","created_at":"2026-05-20T01:05:37.906964+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZBCOYK3LZCSX2WDP","created_at":"2026-05-20T01:05:37.906964+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZBCOYK3L","created_at":"2026-05-20T01:05:37.906964+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/ZBCOYK3LZCSX2WDPMA4AOGMWMJ","json":"https://pith.science/pith/ZBCOYK3LZCSX2WDPMA4AOGMWMJ.json","graph_json":"https://pith.science/api/pith-number/ZBCOYK3LZCSX2WDPMA4AOGMWMJ/graph.json","events_json":"https://pith.science/api/pith-number/ZBCOYK3LZCSX2WDPMA4AOGMWMJ/events.json","paper":"https://pith.science/paper/ZBCOYK3L"},"agent_actions":{"view_html":"https://pith.science/pith/ZBCOYK3LZCSX2WDPMA4AOGMWMJ","download_json":"https://pith.science/pith/ZBCOYK3LZCSX2WDPMA4AOGMWMJ.json","view_paper":"https://pith.science/paper/ZBCOYK3L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.19291&json=true","fetch_graph":"https://pith.science/api/pith-number/ZBCOYK3LZCSX2WDPMA4AOGMWMJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZBCOYK3LZCSX2WDPMA4AOGMWMJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZBCOYK3LZCSX2WDPMA4AOGMWMJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZBCOYK3LZCSX2WDPMA4AOGMWMJ/action/storage_attestation","attest_author":"https://pith.science/pith/ZBCOYK3LZCSX2WDPMA4AOGMWMJ/action/author_attestation","sign_citation":"https://pith.science/pith/ZBCOYK3LZCSX2WDPMA4AOGMWMJ/action/citation_signature","submit_replication":"https://pith.science/pith/ZBCOYK3LZCSX2WDPMA4AOGMWMJ/action/replication_record"}},"created_at":"2026-05-20T01:05:37.906964+00:00","updated_at":"2026-05-20T01:05:37.906964+00:00"}