{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CTDRWTUV5YAZUHCY3EC5ULEZY2","short_pith_number":"pith:CTDRWTUV","schema_version":"1.0","canonical_sha256":"14c71b4e95ee019a1c58d905da2c99c6a1c1bfe03bd5a86aff72d75f50f03a85","source":{"kind":"arxiv","id":"2407.15525","version":2},"attestation_state":"computed","paper":{"title":"Multiple Importance Sampling for Stochastic Gradient Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Corentin Sala\\\"un, Gurprit Singh, Iliyan Georgiev, Niloy J. Mitra, Xingchang Huang","submitted_at":"2024-07-22T10:28:56Z","abstract_excerpt":"We introduce a theoretical and practical framework for efficient importance sampling of mini-batch samples for gradient estimation from single and multiple probability distributions. To handle noisy gradients, our framework dynamically evolves the importance distribution during training by utilizing a self-adaptive metric. Our framework combines multiple, diverse sampling distributions, each tailored to specific parameter gradients. This approach facilitates the importance sampling of vector-valued gradient estimation. Rather than naively combining multiple distributions, our framework involve"},"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":"2407.15525","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-22T10:28:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b09db7f41b2582afd6ca181f0962429b621262d3e8240f5cc4ef5cfd22ec7180","abstract_canon_sha256":"ed7c5931cfc7b24a1717fefefe8d11f44d479d0511f4d731899fe1ceb798e051"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:05.380473Z","signature_b64":"3WeRnPxdJ3wPDKvMKGcrEwLUKbDjSfberWV4oYPak/lD91sP/TwSIYZkjzn4E0I9BMh1PhepA+/LFqEkUTS1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14c71b4e95ee019a1c58d905da2c99c6a1c1bfe03bd5a86aff72d75f50f03a85","last_reissued_at":"2026-07-05T10:06:05.379944Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:05.379944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multiple Importance Sampling for Stochastic Gradient Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Corentin Sala\\\"un, Gurprit Singh, Iliyan Georgiev, Niloy J. Mitra, Xingchang Huang","submitted_at":"2024-07-22T10:28:56Z","abstract_excerpt":"We introduce a theoretical and practical framework for efficient importance sampling of mini-batch samples for gradient estimation from single and multiple probability distributions. To handle noisy gradients, our framework dynamically evolves the importance distribution during training by utilizing a self-adaptive metric. Our framework combines multiple, diverse sampling distributions, each tailored to specific parameter gradients. This approach facilitates the importance sampling of vector-valued gradient estimation. Rather than naively combining multiple distributions, our framework involve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15525","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.15525/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":"2407.15525","created_at":"2026-07-05T10:06:05.380002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15525v2","created_at":"2026-07-05T10:06:05.380002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15525","created_at":"2026-07-05T10:06:05.380002+00:00"},{"alias_kind":"pith_short_12","alias_value":"CTDRWTUV5YAZ","created_at":"2026-07-05T10:06:05.380002+00:00"},{"alias_kind":"pith_short_16","alias_value":"CTDRWTUV5YAZUHCY","created_at":"2026-07-05T10:06:05.380002+00:00"},{"alias_kind":"pith_short_8","alias_value":"CTDRWTUV","created_at":"2026-07-05T10:06:05.380002+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/CTDRWTUV5YAZUHCY3EC5ULEZY2","json":"https://pith.science/pith/CTDRWTUV5YAZUHCY3EC5ULEZY2.json","graph_json":"https://pith.science/api/pith-number/CTDRWTUV5YAZUHCY3EC5ULEZY2/graph.json","events_json":"https://pith.science/api/pith-number/CTDRWTUV5YAZUHCY3EC5ULEZY2/events.json","paper":"https://pith.science/paper/CTDRWTUV"},"agent_actions":{"view_html":"https://pith.science/pith/CTDRWTUV5YAZUHCY3EC5ULEZY2","download_json":"https://pith.science/pith/CTDRWTUV5YAZUHCY3EC5ULEZY2.json","view_paper":"https://pith.science/paper/CTDRWTUV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15525&json=true","fetch_graph":"https://pith.science/api/pith-number/CTDRWTUV5YAZUHCY3EC5ULEZY2/graph.json","fetch_events":"https://pith.science/api/pith-number/CTDRWTUV5YAZUHCY3EC5ULEZY2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CTDRWTUV5YAZUHCY3EC5ULEZY2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CTDRWTUV5YAZUHCY3EC5ULEZY2/action/storage_attestation","attest_author":"https://pith.science/pith/CTDRWTUV5YAZUHCY3EC5ULEZY2/action/author_attestation","sign_citation":"https://pith.science/pith/CTDRWTUV5YAZUHCY3EC5ULEZY2/action/citation_signature","submit_replication":"https://pith.science/pith/CTDRWTUV5YAZUHCY3EC5ULEZY2/action/replication_record"}},"created_at":"2026-07-05T10:06:05.380002+00:00","updated_at":"2026-07-05T10:06:05.380002+00:00"}