{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:XZJUB4DSKJRPQ7TLIV4UK55BNX","short_pith_number":"pith:XZJUB4DS","schema_version":"1.0","canonical_sha256":"be5340f0725262f87e6b45794577a16debb8e34412ab1e868e89ed9ad1346b91","source":{"kind":"arxiv","id":"1511.06343","version":4},"attestation_state":"computed","paper":{"title":"Online Batch Selection for Faster Training of Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","math.OC"],"primary_cat":"cs.LG","authors_text":"Frank Hutter, Ilya Loshchilov","submitted_at":"2015-11-19T20:24:09Z","abstract_excerpt":"Deep neural networks are commonly trained using stochastic non-convex optimization procedures, which are driven by gradient information estimated on fractions (batches) of the dataset. While it is commonly accepted that batch size is an important parameter for offline tuning, the benefits of online selection of batches remain poorly understood. We investigate online batch selection strategies for two state-of-the-art methods of stochastic gradient-based optimization, AdaDelta and Adam. As the loss function to be minimized for the whole dataset is an aggregation of loss functions of individual "},"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":"1511.06343","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T20:24:09Z","cross_cats_sorted":["cs.NE","math.OC"],"title_canon_sha256":"abeda249bedbaad0850defdcbf6463cd3e897272510e6cc28417f76bba6a0868","abstract_canon_sha256":"63333a488696d168b9016542e1da79883c153287ddbfbf08115dc94e807c6c3b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:16:24.560926Z","signature_b64":"ZCCBjf3bNaN47OG3pheKXBogAQK8VPBgiqcHfcmC5zhW5f+xnd5yFTfZR1OZ441OJGFR6kCzkPOiwxuRcVJFCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be5340f0725262f87e6b45794577a16debb8e34412ab1e868e89ed9ad1346b91","last_reissued_at":"2026-05-18T01:16:24.560287Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:16:24.560287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Batch Selection for Faster Training of Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","math.OC"],"primary_cat":"cs.LG","authors_text":"Frank Hutter, Ilya Loshchilov","submitted_at":"2015-11-19T20:24:09Z","abstract_excerpt":"Deep neural networks are commonly trained using stochastic non-convex optimization procedures, which are driven by gradient information estimated on fractions (batches) of the dataset. While it is commonly accepted that batch size is an important parameter for offline tuning, the benefits of online selection of batches remain poorly understood. We investigate online batch selection strategies for two state-of-the-art methods of stochastic gradient-based optimization, AdaDelta and Adam. As the loss function to be minimized for the whole dataset is an aggregation of loss functions of individual "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06343","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":"1511.06343","created_at":"2026-05-18T01:16:24.560407+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.06343v4","created_at":"2026-05-18T01:16:24.560407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06343","created_at":"2026-05-18T01:16:24.560407+00:00"},{"alias_kind":"pith_short_12","alias_value":"XZJUB4DSKJRP","created_at":"2026-05-18T12:29:50.041715+00:00"},{"alias_kind":"pith_short_16","alias_value":"XZJUB4DSKJRPQ7TL","created_at":"2026-05-18T12:29:50.041715+00:00"},{"alias_kind":"pith_short_8","alias_value":"XZJUB4DS","created_at":"2026-05-18T12:29:50.041715+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"1907.01193","citing_title":"Inverse Attention Guided Deep Crowd Counting Network","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2502.12272","citing_title":"Learning to Reason at the Frontier of Learnability","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22644","citing_title":"Why SGD is not Brownian Motion: A New Perspective on Stochastic Dynamics","ref_index":164,"is_internal_anchor":true},{"citing_arxiv_id":"2502.10248","citing_title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","ref_index":268,"is_internal_anchor":true},{"citing_arxiv_id":"2512.05226","citing_title":"Variance Matters: Improving Domain Adaptation via Stratified Sampling","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07063","citing_title":"Dr. Post-Training: A Data Regularization Perspective on LLM Post-Training","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07551","citing_title":"Disagreement-Regularized Importance Sampling for Adversarial Label Corruption","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07397","citing_title":"Data Warmup: Complexity-Aware Curricula for Efficient Diffusion Training","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XZJUB4DSKJRPQ7TLIV4UK55BNX","json":"https://pith.science/pith/XZJUB4DSKJRPQ7TLIV4UK55BNX.json","graph_json":"https://pith.science/api/pith-number/XZJUB4DSKJRPQ7TLIV4UK55BNX/graph.json","events_json":"https://pith.science/api/pith-number/XZJUB4DSKJRPQ7TLIV4UK55BNX/events.json","paper":"https://pith.science/paper/XZJUB4DS"},"agent_actions":{"view_html":"https://pith.science/pith/XZJUB4DSKJRPQ7TLIV4UK55BNX","download_json":"https://pith.science/pith/XZJUB4DSKJRPQ7TLIV4UK55BNX.json","view_paper":"https://pith.science/paper/XZJUB4DS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.06343&json=true","fetch_graph":"https://pith.science/api/pith-number/XZJUB4DSKJRPQ7TLIV4UK55BNX/graph.json","fetch_events":"https://pith.science/api/pith-number/XZJUB4DSKJRPQ7TLIV4UK55BNX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XZJUB4DSKJRPQ7TLIV4UK55BNX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XZJUB4DSKJRPQ7TLIV4UK55BNX/action/storage_attestation","attest_author":"https://pith.science/pith/XZJUB4DSKJRPQ7TLIV4UK55BNX/action/author_attestation","sign_citation":"https://pith.science/pith/XZJUB4DSKJRPQ7TLIV4UK55BNX/action/citation_signature","submit_replication":"https://pith.science/pith/XZJUB4DSKJRPQ7TLIV4UK55BNX/action/replication_record"}},"created_at":"2026-05-18T01:16:24.560407+00:00","updated_at":"2026-05-18T01:16:24.560407+00:00"}