{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RJKOIEKRO4JN72LUZWDRTESG5Z","short_pith_number":"pith:RJKOIEKR","schema_version":"1.0","canonical_sha256":"8a54e411517712dfe974cd87199246ee5da6fa6cad52b9c3fff1d1217c4b20ee","source":{"kind":"arxiv","id":"2101.06070","version":1},"attestation_state":"computed","paper":{"title":"Efficient Semi-Implicit Variational Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexandre Maraval, Haitham Ammar, Hang Ren, Jun Wang, Rasul Tutunov, Vincent Moens","submitted_at":"2021-01-15T11:39:09Z","abstract_excerpt":"In this paper, we propose CI-VI an efficient and scalable solver for semi-implicit variational inference (SIVI). Our method, first, maps SIVI's evidence lower bound (ELBO) to a form involving a nonlinear functional nesting of expected values and then develops a rigorous optimiser capable of correctly handling bias inherent to nonlinear nested expectations using an extrapolation-smoothing mechanism coupled with gradient sketching. Our theoretical results demonstrate convergence to a stationary point of the ELBO in general non-convex settings typically arising when using deep network models and "},"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":"2101.06070","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-15T11:39:09Z","cross_cats_sorted":[],"title_canon_sha256":"c0b955c5d339a921e4612f03bcf1005dbca142900016f6dc3015bf226cb52d3b","abstract_canon_sha256":"8489b7b7a8e59840c07475fd63bfc1d4544abd6ebe6d0c662cbad8190499d7f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:07:10.001614Z","signature_b64":"WHkMk3NA/gwor2g2LGmLY1G6fxUQnTKLivZL3F2j9Kcyc0o5Jko92e+5mUW3wDtivKnXWSovZ9sM7Gg/kdoPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a54e411517712dfe974cd87199246ee5da6fa6cad52b9c3fff1d1217c4b20ee","last_reissued_at":"2026-07-05T02:07:10.001150Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:07:10.001150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Semi-Implicit Variational Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexandre Maraval, Haitham Ammar, Hang Ren, Jun Wang, Rasul Tutunov, Vincent Moens","submitted_at":"2021-01-15T11:39:09Z","abstract_excerpt":"In this paper, we propose CI-VI an efficient and scalable solver for semi-implicit variational inference (SIVI). Our method, first, maps SIVI's evidence lower bound (ELBO) to a form involving a nonlinear functional nesting of expected values and then develops a rigorous optimiser capable of correctly handling bias inherent to nonlinear nested expectations using an extrapolation-smoothing mechanism coupled with gradient sketching. Our theoretical results demonstrate convergence to a stationary point of the ELBO in general non-convex settings typically arising when using deep network models and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.06070","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2101.06070/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":"2101.06070","created_at":"2026-07-05T02:07:10.001211+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.06070v1","created_at":"2026-07-05T02:07:10.001211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.06070","created_at":"2026-07-05T02:07:10.001211+00:00"},{"alias_kind":"pith_short_12","alias_value":"RJKOIEKRO4JN","created_at":"2026-07-05T02:07:10.001211+00:00"},{"alias_kind":"pith_short_16","alias_value":"RJKOIEKRO4JN72LU","created_at":"2026-07-05T02:07:10.001211+00:00"},{"alias_kind":"pith_short_8","alias_value":"RJKOIEKR","created_at":"2026-07-05T02:07:10.001211+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16570","citing_title":"A Cubing Strategy for Identifying Stable Hyperparameter Regions for Uncertainty Quantification in Spatial Deep Learning","ref_index":226,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RJKOIEKRO4JN72LUZWDRTESG5Z","json":"https://pith.science/pith/RJKOIEKRO4JN72LUZWDRTESG5Z.json","graph_json":"https://pith.science/api/pith-number/RJKOIEKRO4JN72LUZWDRTESG5Z/graph.json","events_json":"https://pith.science/api/pith-number/RJKOIEKRO4JN72LUZWDRTESG5Z/events.json","paper":"https://pith.science/paper/RJKOIEKR"},"agent_actions":{"view_html":"https://pith.science/pith/RJKOIEKRO4JN72LUZWDRTESG5Z","download_json":"https://pith.science/pith/RJKOIEKRO4JN72LUZWDRTESG5Z.json","view_paper":"https://pith.science/paper/RJKOIEKR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.06070&json=true","fetch_graph":"https://pith.science/api/pith-number/RJKOIEKRO4JN72LUZWDRTESG5Z/graph.json","fetch_events":"https://pith.science/api/pith-number/RJKOIEKRO4JN72LUZWDRTESG5Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RJKOIEKRO4JN72LUZWDRTESG5Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RJKOIEKRO4JN72LUZWDRTESG5Z/action/storage_attestation","attest_author":"https://pith.science/pith/RJKOIEKRO4JN72LUZWDRTESG5Z/action/author_attestation","sign_citation":"https://pith.science/pith/RJKOIEKRO4JN72LUZWDRTESG5Z/action/citation_signature","submit_replication":"https://pith.science/pith/RJKOIEKRO4JN72LUZWDRTESG5Z/action/replication_record"}},"created_at":"2026-07-05T02:07:10.001211+00:00","updated_at":"2026-07-05T02:07:10.001211+00:00"}