{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JFHDIGOODUFDOHAZKWXQUFJSGL","short_pith_number":"pith:JFHDIGOO","schema_version":"1.0","canonical_sha256":"494e3419ce1d0a371c1955af0a153232f9db4c4ef42fd1b242dab58e638e8e09","source":{"kind":"arxiv","id":"1907.04371","version":5},"attestation_state":"computed","paper":{"title":"Ordered SGD: A New Stochastic Optimization Framework for Empirical Risk Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Haihao Lu, Kenji Kawaguchi","submitted_at":"2019-07-09T19:09:51Z","abstract_excerpt":"We propose a new stochastic optimization framework for empirical risk minimization problems such as those that arise in machine learning. The traditional approaches, such as (mini-batch) stochastic gradient descent (SGD), utilize an unbiased gradient estimator of the empirical average loss. In contrast, we develop a computationally efficient method to construct a gradient estimator that is purposely biased toward those observations with higher current losses. On the theory side, we show that the proposed method minimizes a new ordered modification of the empirical average loss, and is guarante"},"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":"1907.04371","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-07-09T19:09:51Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"b64a2860ff6981306c223165976d753f5ad0a010e6074502727370c6e3807e28","abstract_canon_sha256":"005dfdd7dfc14fcb1bfa6a2bd07144c9333dd3d27c7c5a9ba9345807fea1a690"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:37:46.023249Z","signature_b64":"cLbwdX7ugHp5bAsgxrEs3i0NOD8T+NXeinAiudrW3mOLvpPm9WoYVJEWAE6hJnIyzgUS/OFt/GItdp4iFm9UBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"494e3419ce1d0a371c1955af0a153232f9db4c4ef42fd1b242dab58e638e8e09","last_reissued_at":"2026-07-05T00:37:46.022802Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:37:46.022802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ordered SGD: A New Stochastic Optimization Framework for Empirical Risk Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Haihao Lu, Kenji Kawaguchi","submitted_at":"2019-07-09T19:09:51Z","abstract_excerpt":"We propose a new stochastic optimization framework for empirical risk minimization problems such as those that arise in machine learning. The traditional approaches, such as (mini-batch) stochastic gradient descent (SGD), utilize an unbiased gradient estimator of the empirical average loss. In contrast, we develop a computationally efficient method to construct a gradient estimator that is purposely biased toward those observations with higher current losses. On the theory side, we show that the proposed method minimizes a new ordered modification of the empirical average loss, and is guarante"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.04371","kind":"arxiv","version":5},"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/1907.04371/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":"1907.04371","created_at":"2026-07-05T00:37:46.022857+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.04371v5","created_at":"2026-07-05T00:37:46.022857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.04371","created_at":"2026-07-05T00:37:46.022857+00:00"},{"alias_kind":"pith_short_12","alias_value":"JFHDIGOODUFD","created_at":"2026-07-05T00:37:46.022857+00:00"},{"alias_kind":"pith_short_16","alias_value":"JFHDIGOODUFDOHAZ","created_at":"2026-07-05T00:37:46.022857+00:00"},{"alias_kind":"pith_short_8","alias_value":"JFHDIGOO","created_at":"2026-07-05T00:37:46.022857+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.12272","citing_title":"Learning to Reason at the Frontier of Learnability","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JFHDIGOODUFDOHAZKWXQUFJSGL","json":"https://pith.science/pith/JFHDIGOODUFDOHAZKWXQUFJSGL.json","graph_json":"https://pith.science/api/pith-number/JFHDIGOODUFDOHAZKWXQUFJSGL/graph.json","events_json":"https://pith.science/api/pith-number/JFHDIGOODUFDOHAZKWXQUFJSGL/events.json","paper":"https://pith.science/paper/JFHDIGOO"},"agent_actions":{"view_html":"https://pith.science/pith/JFHDIGOODUFDOHAZKWXQUFJSGL","download_json":"https://pith.science/pith/JFHDIGOODUFDOHAZKWXQUFJSGL.json","view_paper":"https://pith.science/paper/JFHDIGOO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.04371&json=true","fetch_graph":"https://pith.science/api/pith-number/JFHDIGOODUFDOHAZKWXQUFJSGL/graph.json","fetch_events":"https://pith.science/api/pith-number/JFHDIGOODUFDOHAZKWXQUFJSGL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JFHDIGOODUFDOHAZKWXQUFJSGL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JFHDIGOODUFDOHAZKWXQUFJSGL/action/storage_attestation","attest_author":"https://pith.science/pith/JFHDIGOODUFDOHAZKWXQUFJSGL/action/author_attestation","sign_citation":"https://pith.science/pith/JFHDIGOODUFDOHAZKWXQUFJSGL/action/citation_signature","submit_replication":"https://pith.science/pith/JFHDIGOODUFDOHAZKWXQUFJSGL/action/replication_record"}},"created_at":"2026-07-05T00:37:46.022857+00:00","updated_at":"2026-07-05T00:37:46.022857+00:00"}