{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:5TN4S43LROTOSLPQOKVNKZBI7P","short_pith_number":"pith:5TN4S43L","schema_version":"1.0","canonical_sha256":"ecdbc9736b8ba6e92df072aad56428fbe9a842a702fb87fa1858ef85b72bff47","source":{"kind":"arxiv","id":"1712.01038","version":1},"attestation_state":"computed","paper":{"title":"Vprop: Variational Inference using RMSprop","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Mohammad Emtiyaz Khan, Voot Tangkaratt, Yarin Gal, Zuozhu Liu","submitted_at":"2017-12-04T12:31:36Z","abstract_excerpt":"Many computationally-efficient methods for Bayesian deep learning rely on continuous optimization algorithms, but the implementation of these methods requires significant changes to existing code-bases. In this paper, we propose Vprop, a method for Gaussian variational inference that can be implemented with two minor changes to the off-the-shelf RMSprop optimizer. Vprop also reduces the memory requirements of Black-Box Variational Inference by half. We derive Vprop using the conjugate-computation variational inference method, and establish its connections to Newton's method, natural-gradient m"},"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":"1712.01038","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-04T12:31:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8595da167a713ff27bba67da7a22cfebc28728ec498fd9395e57c2ea2c24fc3b","abstract_canon_sha256":"6af1ed88ce3f572f66f6e2906a784b1ccd93e79e82c3b6f986c1ff4f91f0a3a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:59.667924Z","signature_b64":"pptqrQsj4axfNzy3yqFg3B9PwKribB8nf7IKVfWDleKGf2yegLMv1zmvKdtobSXMcGX5yEWp/xGxPVJVi4AkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecdbc9736b8ba6e92df072aad56428fbe9a842a702fb87fa1858ef85b72bff47","last_reissued_at":"2026-05-18T00:28:59.667529Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:59.667529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vprop: Variational Inference using RMSprop","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Mohammad Emtiyaz Khan, Voot Tangkaratt, Yarin Gal, Zuozhu Liu","submitted_at":"2017-12-04T12:31:36Z","abstract_excerpt":"Many computationally-efficient methods for Bayesian deep learning rely on continuous optimization algorithms, but the implementation of these methods requires significant changes to existing code-bases. In this paper, we propose Vprop, a method for Gaussian variational inference that can be implemented with two minor changes to the off-the-shelf RMSprop optimizer. Vprop also reduces the memory requirements of Black-Box Variational Inference by half. We derive Vprop using the conjugate-computation variational inference method, and establish its connections to Newton's method, natural-gradient m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.01038","kind":"arxiv","version":1},"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":"1712.01038","created_at":"2026-05-18T00:28:59.667596+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.01038v1","created_at":"2026-05-18T00:28:59.667596+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.01038","created_at":"2026-05-18T00:28:59.667596+00:00"},{"alias_kind":"pith_short_12","alias_value":"5TN4S43LROTO","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"5TN4S43LROTOSLPQ","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"5TN4S43L","created_at":"2026-05-18T12:31:00.734936+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/5TN4S43LROTOSLPQOKVNKZBI7P","json":"https://pith.science/pith/5TN4S43LROTOSLPQOKVNKZBI7P.json","graph_json":"https://pith.science/api/pith-number/5TN4S43LROTOSLPQOKVNKZBI7P/graph.json","events_json":"https://pith.science/api/pith-number/5TN4S43LROTOSLPQOKVNKZBI7P/events.json","paper":"https://pith.science/paper/5TN4S43L"},"agent_actions":{"view_html":"https://pith.science/pith/5TN4S43LROTOSLPQOKVNKZBI7P","download_json":"https://pith.science/pith/5TN4S43LROTOSLPQOKVNKZBI7P.json","view_paper":"https://pith.science/paper/5TN4S43L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.01038&json=true","fetch_graph":"https://pith.science/api/pith-number/5TN4S43LROTOSLPQOKVNKZBI7P/graph.json","fetch_events":"https://pith.science/api/pith-number/5TN4S43LROTOSLPQOKVNKZBI7P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5TN4S43LROTOSLPQOKVNKZBI7P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5TN4S43LROTOSLPQOKVNKZBI7P/action/storage_attestation","attest_author":"https://pith.science/pith/5TN4S43LROTOSLPQOKVNKZBI7P/action/author_attestation","sign_citation":"https://pith.science/pith/5TN4S43LROTOSLPQOKVNKZBI7P/action/citation_signature","submit_replication":"https://pith.science/pith/5TN4S43LROTOSLPQOKVNKZBI7P/action/replication_record"}},"created_at":"2026-05-18T00:28:59.667596+00:00","updated_at":"2026-05-18T00:28:59.667596+00:00"}