{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:X3TQMC3GPUE3IZABYWX2TN64XG","short_pith_number":"pith:X3TQMC3G","schema_version":"1.0","canonical_sha256":"bee7060b667d09b46401c5afa9b7dcb9bcda80efee6234a3e77f559e1e0f0a4f","source":{"kind":"arxiv","id":"1711.06424","version":3},"attestation_state":"computed","paper":{"title":"A Resizable Mini-batch Gradient Descent based on a Multi-Armed Bandit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chang D. Yoo, Seong Jin Cho, Sunghun Kang","submitted_at":"2017-11-17T06:21:47Z","abstract_excerpt":"Determining the appropriate batch size for mini-batch gradient descent is always time consuming as it often relies on grid search. This paper considers a resizable mini-batch gradient descent (RMGD) algorithm based on a multi-armed bandit for achieving best performance in grid search by selecting an appropriate batch size at each epoch with a probability defined as a function of its previous success/failure. This probability encourages exploration of different batch size and then later exploitation of batch size with history of success. At each epoch, the RMGD samples a batch size from its pro"},"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":"1711.06424","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-17T06:21:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f7ae76dfc531d20dd7c8501d526faea24bbb909765d565751e099e227cc27902","abstract_canon_sha256":"ef3238c9b434435f6a849d050bed205dfa85f4b4802ecbd1e7fb807b0e48f881"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:27.316990Z","signature_b64":"fuu59viXlrY1UPZzCI4FyK3RSUBH9nEqtwzIbuW0vQmv3SWjLnin4Q9G7jpJNV/WREk9yx7yVS1tDE7i5w2vBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bee7060b667d09b46401c5afa9b7dcb9bcda80efee6234a3e77f559e1e0f0a4f","last_reissued_at":"2026-05-18T00:22:27.316272Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:27.316272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Resizable Mini-batch Gradient Descent based on a Multi-Armed Bandit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chang D. Yoo, Seong Jin Cho, Sunghun Kang","submitted_at":"2017-11-17T06:21:47Z","abstract_excerpt":"Determining the appropriate batch size for mini-batch gradient descent is always time consuming as it often relies on grid search. This paper considers a resizable mini-batch gradient descent (RMGD) algorithm based on a multi-armed bandit for achieving best performance in grid search by selecting an appropriate batch size at each epoch with a probability defined as a function of its previous success/failure. This probability encourages exploration of different batch size and then later exploitation of batch size with history of success. At each epoch, the RMGD samples a batch size from its pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.06424","kind":"arxiv","version":3},"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":"1711.06424","created_at":"2026-05-18T00:22:27.316410+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.06424v3","created_at":"2026-05-18T00:22:27.316410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.06424","created_at":"2026-05-18T00:22:27.316410+00:00"},{"alias_kind":"pith_short_12","alias_value":"X3TQMC3GPUE3","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"X3TQMC3GPUE3IZAB","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"X3TQMC3G","created_at":"2026-05-18T12:31:53.515858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2102.01293","citing_title":"Scaling Laws for Transfer","ref_index":129,"is_internal_anchor":true},{"citing_arxiv_id":"2112.00861","citing_title":"A General Language Assistant as a Laboratory for Alignment","ref_index":171,"is_internal_anchor":false},{"citing_arxiv_id":"2207.05221","citing_title":"Language Models (Mostly) Know What They Know","ref_index":248,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X3TQMC3GPUE3IZABYWX2TN64XG","json":"https://pith.science/pith/X3TQMC3GPUE3IZABYWX2TN64XG.json","graph_json":"https://pith.science/api/pith-number/X3TQMC3GPUE3IZABYWX2TN64XG/graph.json","events_json":"https://pith.science/api/pith-number/X3TQMC3GPUE3IZABYWX2TN64XG/events.json","paper":"https://pith.science/paper/X3TQMC3G"},"agent_actions":{"view_html":"https://pith.science/pith/X3TQMC3GPUE3IZABYWX2TN64XG","download_json":"https://pith.science/pith/X3TQMC3GPUE3IZABYWX2TN64XG.json","view_paper":"https://pith.science/paper/X3TQMC3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.06424&json=true","fetch_graph":"https://pith.science/api/pith-number/X3TQMC3GPUE3IZABYWX2TN64XG/graph.json","fetch_events":"https://pith.science/api/pith-number/X3TQMC3GPUE3IZABYWX2TN64XG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X3TQMC3GPUE3IZABYWX2TN64XG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X3TQMC3GPUE3IZABYWX2TN64XG/action/storage_attestation","attest_author":"https://pith.science/pith/X3TQMC3GPUE3IZABYWX2TN64XG/action/author_attestation","sign_citation":"https://pith.science/pith/X3TQMC3GPUE3IZABYWX2TN64XG/action/citation_signature","submit_replication":"https://pith.science/pith/X3TQMC3GPUE3IZABYWX2TN64XG/action/replication_record"}},"created_at":"2026-05-18T00:22:27.316410+00:00","updated_at":"2026-05-18T00:22:27.316410+00:00"}