{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:H7JGZD46HR4VGTEJ25ZZ2GSFSX","short_pith_number":"pith:H7JGZD46","schema_version":"1.0","canonical_sha256":"3fd26c8f9e3c79534c89d7739d1a4595f020f84c6bfd522c1533dd875bc929b1","source":{"kind":"arxiv","id":"1903.04192","version":1},"attestation_state":"computed","paper":{"title":"Accelerating Minibatch Stochastic Gradient Descent using Typicality Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fei-Yue Wang, Li Li, Xinyu Peng","submitted_at":"2019-03-11T09:57:18Z","abstract_excerpt":"Machine learning, especially deep neural networks, has been rapidly developed in fields including computer vision, speech recognition and reinforcement learning. Although Mini-batch SGD is one of the most popular stochastic optimization methods in training deep networks, it shows a slow convergence rate due to the large noise in gradient approximation. In this paper, we attempt to remedy this problem by building more efficient batch selection method based on typicality sampling, which reduces the error of gradient estimation in conventional Minibatch SGD. We analyze the convergence rate of the"},"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":"1903.04192","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-11T09:57:18Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"c97835833da678d2d280f6d1de58c1a6e170139d9109b767886dbd9f600e436d","abstract_canon_sha256":"3e4372b7c8bf7d6146f187fefd77652a54a081606fa139ab58f77ff54a766bca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:36.263464Z","signature_b64":"9MtFLGH0gikbrIN/e9iw60wp/OZ0pYakOyQavbUrLG0vJeUr1QVF5+uOEIa9zpggW5FGpjCitSZ4l+pHNo9jCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fd26c8f9e3c79534c89d7739d1a4595f020f84c6bfd522c1533dd875bc929b1","last_reissued_at":"2026-05-17T23:51:36.262606Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:36.262606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerating Minibatch Stochastic Gradient Descent using Typicality Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fei-Yue Wang, Li Li, Xinyu Peng","submitted_at":"2019-03-11T09:57:18Z","abstract_excerpt":"Machine learning, especially deep neural networks, has been rapidly developed in fields including computer vision, speech recognition and reinforcement learning. Although Mini-batch SGD is one of the most popular stochastic optimization methods in training deep networks, it shows a slow convergence rate due to the large noise in gradient approximation. In this paper, we attempt to remedy this problem by building more efficient batch selection method based on typicality sampling, which reduces the error of gradient estimation in conventional Minibatch SGD. We analyze the convergence rate of the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.04192","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":""},"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":"1903.04192","created_at":"2026-05-17T23:51:36.262767+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.04192v1","created_at":"2026-05-17T23:51:36.262767+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.04192","created_at":"2026-05-17T23:51:36.262767+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7JGZD46HR4V","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7JGZD46HR4VGTEJ","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7JGZD46","created_at":"2026-05-18T12:33:18.533446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06350","citing_title":"Convergence of Riemannian Stochastic Gradient Descents: Varying Batch Sizes And Nonstandard Batch Forming","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H7JGZD46HR4VGTEJ25ZZ2GSFSX","json":"https://pith.science/pith/H7JGZD46HR4VGTEJ25ZZ2GSFSX.json","graph_json":"https://pith.science/api/pith-number/H7JGZD46HR4VGTEJ25ZZ2GSFSX/graph.json","events_json":"https://pith.science/api/pith-number/H7JGZD46HR4VGTEJ25ZZ2GSFSX/events.json","paper":"https://pith.science/paper/H7JGZD46"},"agent_actions":{"view_html":"https://pith.science/pith/H7JGZD46HR4VGTEJ25ZZ2GSFSX","download_json":"https://pith.science/pith/H7JGZD46HR4VGTEJ25ZZ2GSFSX.json","view_paper":"https://pith.science/paper/H7JGZD46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.04192&json=true","fetch_graph":"https://pith.science/api/pith-number/H7JGZD46HR4VGTEJ25ZZ2GSFSX/graph.json","fetch_events":"https://pith.science/api/pith-number/H7JGZD46HR4VGTEJ25ZZ2GSFSX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7JGZD46HR4VGTEJ25ZZ2GSFSX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7JGZD46HR4VGTEJ25ZZ2GSFSX/action/storage_attestation","attest_author":"https://pith.science/pith/H7JGZD46HR4VGTEJ25ZZ2GSFSX/action/author_attestation","sign_citation":"https://pith.science/pith/H7JGZD46HR4VGTEJ25ZZ2GSFSX/action/citation_signature","submit_replication":"https://pith.science/pith/H7JGZD46HR4VGTEJ25ZZ2GSFSX/action/replication_record"}},"created_at":"2026-05-17T23:51:36.262767+00:00","updated_at":"2026-05-17T23:51:36.262767+00:00"}