{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RJ36D7GNKYPZ46PNGXKEBT3IRW","short_pith_number":"pith:RJ36D7GN","schema_version":"1.0","canonical_sha256":"8a77e1fccd561f9e79ed35d440cf688db526bebf6da97a4ee7a7665fae7adf1e","source":{"kind":"arxiv","id":"1804.02772","version":2},"attestation_state":"computed","paper":{"title":"Active Mini-Batch Sampling using Repulsive Point Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Cengiz \\\"Oztireli, Cheng Zhang, Giampiero Salvi, Stephan Mandt","submitted_at":"2018-04-08T22:48:20Z","abstract_excerpt":"The convergence speed of stochastic gradient descent (SGD) can be improved by actively selecting mini-batches. We explore sampling schemes where similar data points are less likely to be selected in the same mini-batch. In particular, we prove that such repulsive sampling schemes lowers the variance of the gradient estimator. This generalizes recent work on using Determinantal Point Processes (DPPs) for mini-batch diversification (Zhang et al., 2017) to the broader class of repulsive point processes. We first show that the phenomenon of variance reduction by diversified sampling generalizes in"},"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":"1804.02772","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-04-08T22:48:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5b613e59505ce27ad417963cf7b4ab092400bfb8fa8f3632c926f9794c68a2b5","abstract_canon_sha256":"d439981b41fe6c6b095836d678840909e5731e26dee4ab234cecf8fe264c7f28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:48.168129Z","signature_b64":"PFrxl0RaqDruQD6ExxWBJTQ28BQ/L52MCPUxYsrDQa40fE7e8no+V8GYL+RdmFNKEqJpUkZTVvNeJXJWTqWNCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a77e1fccd561f9e79ed35d440cf688db526bebf6da97a4ee7a7665fae7adf1e","last_reissued_at":"2026-05-18T00:12:48.167404Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:48.167404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Active Mini-Batch Sampling using Repulsive Point Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Cengiz \\\"Oztireli, Cheng Zhang, Giampiero Salvi, Stephan Mandt","submitted_at":"2018-04-08T22:48:20Z","abstract_excerpt":"The convergence speed of stochastic gradient descent (SGD) can be improved by actively selecting mini-batches. We explore sampling schemes where similar data points are less likely to be selected in the same mini-batch. In particular, we prove that such repulsive sampling schemes lowers the variance of the gradient estimator. This generalizes recent work on using Determinantal Point Processes (DPPs) for mini-batch diversification (Zhang et al., 2017) to the broader class of repulsive point processes. We first show that the phenomenon of variance reduction by diversified sampling generalizes in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.02772","kind":"arxiv","version":2},"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":"1804.02772","created_at":"2026-05-18T00:12:48.167525+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.02772v2","created_at":"2026-05-18T00:12:48.167525+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.02772","created_at":"2026-05-18T00:12:48.167525+00:00"},{"alias_kind":"pith_short_12","alias_value":"RJ36D7GNKYPZ","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RJ36D7GNKYPZ46PN","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RJ36D7GN","created_at":"2026-05-18T12:32:50.500415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.08771","citing_title":"Submodular Batch Selection for Training Deep Neural Networks","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RJ36D7GNKYPZ46PNGXKEBT3IRW","json":"https://pith.science/pith/RJ36D7GNKYPZ46PNGXKEBT3IRW.json","graph_json":"https://pith.science/api/pith-number/RJ36D7GNKYPZ46PNGXKEBT3IRW/graph.json","events_json":"https://pith.science/api/pith-number/RJ36D7GNKYPZ46PNGXKEBT3IRW/events.json","paper":"https://pith.science/paper/RJ36D7GN"},"agent_actions":{"view_html":"https://pith.science/pith/RJ36D7GNKYPZ46PNGXKEBT3IRW","download_json":"https://pith.science/pith/RJ36D7GNKYPZ46PNGXKEBT3IRW.json","view_paper":"https://pith.science/paper/RJ36D7GN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.02772&json=true","fetch_graph":"https://pith.science/api/pith-number/RJ36D7GNKYPZ46PNGXKEBT3IRW/graph.json","fetch_events":"https://pith.science/api/pith-number/RJ36D7GNKYPZ46PNGXKEBT3IRW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RJ36D7GNKYPZ46PNGXKEBT3IRW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RJ36D7GNKYPZ46PNGXKEBT3IRW/action/storage_attestation","attest_author":"https://pith.science/pith/RJ36D7GNKYPZ46PNGXKEBT3IRW/action/author_attestation","sign_citation":"https://pith.science/pith/RJ36D7GNKYPZ46PNGXKEBT3IRW/action/citation_signature","submit_replication":"https://pith.science/pith/RJ36D7GNKYPZ46PNGXKEBT3IRW/action/replication_record"}},"created_at":"2026-05-18T00:12:48.167525+00:00","updated_at":"2026-05-18T00:12:48.167525+00:00"}