{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JMHSAZXB4GHOVUZ2MB66VV2ZY7","short_pith_number":"pith:JMHSAZXB","schema_version":"1.0","canonical_sha256":"4b0f2066e1e18eead33a607dead759c7caa910a383d3985cc279f69dd9ac72f2","source":{"kind":"arxiv","id":"2402.05264","version":1},"attestation_state":"computed","paper":{"title":"AdaBatchGrad: Combining Adaptive Batch Size and Adaptive Step Size","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Aigerim Zhumabayeva, Alexander Gasnikov, Chulu Xiang, Dmitry Kamzolov, Martin Tak\\'a\\v{c}, Petr Ostroukhov","submitted_at":"2024-02-07T21:19:05Z","abstract_excerpt":"This paper presents a novel adaptation of the Stochastic Gradient Descent (SGD), termed AdaBatchGrad. This modification seamlessly integrates an adaptive step size with an adjustable batch size. An increase in batch size and a decrease in step size are well-known techniques to tighten the area of convergence of SGD and decrease its variance. A range of studies by R. Byrd and J. Nocedal introduced various testing techniques to assess the quality of mini-batch gradient approximations and choose the appropriate batch sizes at every step. Methods that utilized exact tests were observed to converge"},"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":"2402.05264","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-07T21:19:05Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"c2625aa0de2aedfe6ada2fc77fad670551de7c150503e031935ed74adf01fe0b","abstract_canon_sha256":"5f81b5a3050becfe77efe451c9481781ad29ba1b2f3a1212d61e6de5f590e85c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:47.128600Z","signature_b64":"t/152MNCdhukPGF0S1ooCPEjL8Fw5AT9xY040FWfH3GG1pGjlnByUJxfHlPpOIXjZQP7nOqQg8xTMgzQkX8GBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b0f2066e1e18eead33a607dead759c7caa910a383d3985cc279f69dd9ac72f2","last_reissued_at":"2026-07-05T07:42:47.128145Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:47.128145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaBatchGrad: Combining Adaptive Batch Size and Adaptive Step Size","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Aigerim Zhumabayeva, Alexander Gasnikov, Chulu Xiang, Dmitry Kamzolov, Martin Tak\\'a\\v{c}, Petr Ostroukhov","submitted_at":"2024-02-07T21:19:05Z","abstract_excerpt":"This paper presents a novel adaptation of the Stochastic Gradient Descent (SGD), termed AdaBatchGrad. This modification seamlessly integrates an adaptive step size with an adjustable batch size. An increase in batch size and a decrease in step size are well-known techniques to tighten the area of convergence of SGD and decrease its variance. A range of studies by R. Byrd and J. Nocedal introduced various testing techniques to assess the quality of mini-batch gradient approximations and choose the appropriate batch sizes at every step. Methods that utilized exact tests were observed to converge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05264","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/2402.05264/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":"2402.05264","created_at":"2026-07-05T07:42:47.128202+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.05264v1","created_at":"2026-07-05T07:42:47.128202+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05264","created_at":"2026-07-05T07:42:47.128202+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMHSAZXB4GHO","created_at":"2026-07-05T07:42:47.128202+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMHSAZXB4GHOVUZ2","created_at":"2026-07-05T07:42:47.128202+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMHSAZXB","created_at":"2026-07-05T07:42:47.128202+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.21124","citing_title":"Adaptive Batch Size Schedules for Distributed Training of Language Models with Data and Model Parallelism","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JMHSAZXB4GHOVUZ2MB66VV2ZY7","json":"https://pith.science/pith/JMHSAZXB4GHOVUZ2MB66VV2ZY7.json","graph_json":"https://pith.science/api/pith-number/JMHSAZXB4GHOVUZ2MB66VV2ZY7/graph.json","events_json":"https://pith.science/api/pith-number/JMHSAZXB4GHOVUZ2MB66VV2ZY7/events.json","paper":"https://pith.science/paper/JMHSAZXB"},"agent_actions":{"view_html":"https://pith.science/pith/JMHSAZXB4GHOVUZ2MB66VV2ZY7","download_json":"https://pith.science/pith/JMHSAZXB4GHOVUZ2MB66VV2ZY7.json","view_paper":"https://pith.science/paper/JMHSAZXB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.05264&json=true","fetch_graph":"https://pith.science/api/pith-number/JMHSAZXB4GHOVUZ2MB66VV2ZY7/graph.json","fetch_events":"https://pith.science/api/pith-number/JMHSAZXB4GHOVUZ2MB66VV2ZY7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMHSAZXB4GHOVUZ2MB66VV2ZY7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMHSAZXB4GHOVUZ2MB66VV2ZY7/action/storage_attestation","attest_author":"https://pith.science/pith/JMHSAZXB4GHOVUZ2MB66VV2ZY7/action/author_attestation","sign_citation":"https://pith.science/pith/JMHSAZXB4GHOVUZ2MB66VV2ZY7/action/citation_signature","submit_replication":"https://pith.science/pith/JMHSAZXB4GHOVUZ2MB66VV2ZY7/action/replication_record"}},"created_at":"2026-07-05T07:42:47.128202+00:00","updated_at":"2026-07-05T07:42:47.128202+00:00"}