{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:GCNY26W5KHPO67FSDQVW5UNCLW","short_pith_number":"pith:GCNY26W5","schema_version":"1.0","canonical_sha256":"309b8d7add51deef7cb21c2b6ed1a25d9ca503cdc7022968837c3e2ae2805383","source":{"kind":"arxiv","id":"1802.04715","version":3},"attestation_state":"computed","paper":{"title":"Online Variance Reduction for Stochastic Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andreas Krause, Kfir Y. Levy, Zal\\'an Borsos","submitted_at":"2018-02-13T16:28:45Z","abstract_excerpt":"Modern stochastic optimization methods often rely on uniform sampling which is agnostic to the underlying characteristics of the data. This might degrade the convergence by yielding estimates that suffer from a high variance. A possible remedy is to employ non-uniform importance sampling techniques, which take the structure of the dataset into account. In this work, we investigate a recently proposed setting which poses variance reduction as an online optimization problem with bandit feedback. We devise a novel and efficient algorithm for this setting that finds a sequence of importance sampli"},"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":"1802.04715","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-13T16:28:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a0dca16148a9d0d027015d641b0ac55aa04d6e72638f396de3de6113b2aaa90e","abstract_canon_sha256":"d712bc34a52c44b18db989770d9e67b829582fec52c55b3f9055595c74641a7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:06.333159Z","signature_b64":"Yxt7daT2KM2xtMhdAkx72tIh1HuvgAxV9U0NlfOAlQcnKRDiNA42tCZYZZmvH/DsoTLL5r5JH0NHhj3R2AEkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"309b8d7add51deef7cb21c2b6ed1a25d9ca503cdc7022968837c3e2ae2805383","last_reissued_at":"2026-05-18T00:14:06.332673Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:06.332673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Variance Reduction for Stochastic Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andreas Krause, Kfir Y. Levy, Zal\\'an Borsos","submitted_at":"2018-02-13T16:28:45Z","abstract_excerpt":"Modern stochastic optimization methods often rely on uniform sampling which is agnostic to the underlying characteristics of the data. This might degrade the convergence by yielding estimates that suffer from a high variance. A possible remedy is to employ non-uniform importance sampling techniques, which take the structure of the dataset into account. In this work, we investigate a recently proposed setting which poses variance reduction as an online optimization problem with bandit feedback. We devise a novel and efficient algorithm for this setting that finds a sequence of importance sampli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04715","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":"1802.04715","created_at":"2026-05-18T00:14:06.332746+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.04715v3","created_at":"2026-05-18T00:14:06.332746+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04715","created_at":"2026-05-18T00:14:06.332746+00:00"},{"alias_kind":"pith_short_12","alias_value":"GCNY26W5KHPO","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"GCNY26W5KHPO67FS","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"GCNY26W5","created_at":"2026-05-18T12:32:25.280505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GCNY26W5KHPO67FSDQVW5UNCLW","json":"https://pith.science/pith/GCNY26W5KHPO67FSDQVW5UNCLW.json","graph_json":"https://pith.science/api/pith-number/GCNY26W5KHPO67FSDQVW5UNCLW/graph.json","events_json":"https://pith.science/api/pith-number/GCNY26W5KHPO67FSDQVW5UNCLW/events.json","paper":"https://pith.science/paper/GCNY26W5"},"agent_actions":{"view_html":"https://pith.science/pith/GCNY26W5KHPO67FSDQVW5UNCLW","download_json":"https://pith.science/pith/GCNY26W5KHPO67FSDQVW5UNCLW.json","view_paper":"https://pith.science/paper/GCNY26W5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.04715&json=true","fetch_graph":"https://pith.science/api/pith-number/GCNY26W5KHPO67FSDQVW5UNCLW/graph.json","fetch_events":"https://pith.science/api/pith-number/GCNY26W5KHPO67FSDQVW5UNCLW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GCNY26W5KHPO67FSDQVW5UNCLW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GCNY26W5KHPO67FSDQVW5UNCLW/action/storage_attestation","attest_author":"https://pith.science/pith/GCNY26W5KHPO67FSDQVW5UNCLW/action/author_attestation","sign_citation":"https://pith.science/pith/GCNY26W5KHPO67FSDQVW5UNCLW/action/citation_signature","submit_replication":"https://pith.science/pith/GCNY26W5KHPO67FSDQVW5UNCLW/action/replication_record"}},"created_at":"2026-05-18T00:14:06.332746+00:00","updated_at":"2026-05-18T00:14:06.332746+00:00"}