{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GZOJU5NKZXVHHSF5Q46TU4FAWD","short_pith_number":"pith:GZOJU5NK","schema_version":"1.0","canonical_sha256":"365c9a75aacdea73c8bd873d3a70a0b0cb6fe99de7dc25edd3212e781a5403a1","source":{"kind":"arxiv","id":"1910.13398","version":3},"attestation_state":"computed","paper":{"title":"Stein's Lemma for the Reparameterization Trick with Exponential Family Mixtures","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Mark Schmidt, Mohammad Emtiyaz Khan, Wu Lin","submitted_at":"2019-10-29T16:59:22Z","abstract_excerpt":"Stein's method (Stein, 1973; 1981) is a powerful tool for statistical applications and has significantly impacted machine learning. Stein's lemma plays an essential role in Stein's method. Previous applications of Stein's lemma either required strong technical assumptions or were limited to Gaussian distributions with restricted covariance structures. In this work, we extend Stein's lemma to exponential-family mixture distributions, including Gaussian distributions with full covariance structures. Our generalization enables us to establish a connection between Stein's lemma and the reparameter"},"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":"1910.13398","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2019-10-29T16:59:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0246d638d115a45c751674c94dadfd3d211c1764cec1e2e3fce4899d932ed453","abstract_canon_sha256":"126d31c04782280dde6a37dedf99a5ccd8d6d0bad0cd8ac53b606be2ff08522e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:08.644940Z","signature_b64":"rZseLYFBgCT/3UVEahIBotgoA2HQajPjJlz0H0lyx5/kjqcW51KIr8VAXLmkHhnwoPVgLU37P6BttC+g9OGXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"365c9a75aacdea73c8bd873d3a70a0b0cb6fe99de7dc25edd3212e781a5403a1","last_reissued_at":"2026-07-05T10:08:08.644595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:08.644595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stein's Lemma for the Reparameterization Trick with Exponential Family Mixtures","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Mark Schmidt, Mohammad Emtiyaz Khan, Wu Lin","submitted_at":"2019-10-29T16:59:22Z","abstract_excerpt":"Stein's method (Stein, 1973; 1981) is a powerful tool for statistical applications and has significantly impacted machine learning. Stein's lemma plays an essential role in Stein's method. Previous applications of Stein's lemma either required strong technical assumptions or were limited to Gaussian distributions with restricted covariance structures. In this work, we extend Stein's lemma to exponential-family mixture distributions, including Gaussian distributions with full covariance structures. Our generalization enables us to establish a connection between Stein's lemma and the reparameter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.13398","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1910.13398/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":"1910.13398","created_at":"2026-07-05T10:08:08.644651+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.13398v3","created_at":"2026-07-05T10:08:08.644651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.13398","created_at":"2026-07-05T10:08:08.644651+00:00"},{"alias_kind":"pith_short_12","alias_value":"GZOJU5NKZXVH","created_at":"2026-07-05T10:08:08.644651+00:00"},{"alias_kind":"pith_short_16","alias_value":"GZOJU5NKZXVHHSF5","created_at":"2026-07-05T10:08:08.644651+00:00"},{"alias_kind":"pith_short_8","alias_value":"GZOJU5NK","created_at":"2026-07-05T10:08:08.644651+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04935","citing_title":"What Type of Inference is Active Inference?","ref_index":192,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20658","citing_title":"Expected Free Energy-based Planning as Variational Inference","ref_index":176,"is_internal_anchor":false},{"citing_arxiv_id":"2304.12906","citing_title":"The Score-Difference Flow for Implicit Generative Modeling","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2602.18718","citing_title":"Stochastic Gradient Variational Inference with Price's Gradient Estimator from Bures-Wasserstein to Parameter Space","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GZOJU5NKZXVHHSF5Q46TU4FAWD","json":"https://pith.science/pith/GZOJU5NKZXVHHSF5Q46TU4FAWD.json","graph_json":"https://pith.science/api/pith-number/GZOJU5NKZXVHHSF5Q46TU4FAWD/graph.json","events_json":"https://pith.science/api/pith-number/GZOJU5NKZXVHHSF5Q46TU4FAWD/events.json","paper":"https://pith.science/paper/GZOJU5NK"},"agent_actions":{"view_html":"https://pith.science/pith/GZOJU5NKZXVHHSF5Q46TU4FAWD","download_json":"https://pith.science/pith/GZOJU5NKZXVHHSF5Q46TU4FAWD.json","view_paper":"https://pith.science/paper/GZOJU5NK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.13398&json=true","fetch_graph":"https://pith.science/api/pith-number/GZOJU5NKZXVHHSF5Q46TU4FAWD/graph.json","fetch_events":"https://pith.science/api/pith-number/GZOJU5NKZXVHHSF5Q46TU4FAWD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GZOJU5NKZXVHHSF5Q46TU4FAWD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GZOJU5NKZXVHHSF5Q46TU4FAWD/action/storage_attestation","attest_author":"https://pith.science/pith/GZOJU5NKZXVHHSF5Q46TU4FAWD/action/author_attestation","sign_citation":"https://pith.science/pith/GZOJU5NKZXVHHSF5Q46TU4FAWD/action/citation_signature","submit_replication":"https://pith.science/pith/GZOJU5NKZXVHHSF5Q46TU4FAWD/action/replication_record"}},"created_at":"2026-07-05T10:08:08.644651+00:00","updated_at":"2026-07-05T10:08:08.644651+00:00"}