{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:G4H2SLFP4WN4QN3BPTN4B3U27C","short_pith_number":"pith:G4H2SLFP","schema_version":"1.0","canonical_sha256":"370fa92cafe59bc837617cdbc0ee9af8be765e56e967f91d57b221ca130317b4","source":{"kind":"arxiv","id":"1707.09714","version":2},"attestation_state":"computed","paper":{"title":"A Geometric Variational Approach to Bayesian Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Abhijoy Saha, Karthik Bharath, Sebastian Kurtek","submitted_at":"2017-07-31T03:59:00Z","abstract_excerpt":"We propose a novel Riemannian geometric framework for variational inference in Bayesian models based on the nonparametric Fisher-Rao metric on the manifold of probability density functions. Under the square-root density representation, the manifold can be identified with the positive orthant of the unit hypersphere in L2, and the Fisher-Rao metric reduces to the standard L2 metric. Exploiting such a Riemannian structure, we formulate the task of approximating the posterior distribution as a variational problem on the hypersphere based on the alpha-divergence. This provides a tighter lower boun"},"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":"1707.09714","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2017-07-31T03:59:00Z","cross_cats_sorted":[],"title_canon_sha256":"db8868b8f384d812fd6935137d60ebdc38a1dac2307746eeee1c421bbb3b2fec","abstract_canon_sha256":"7260c8d6b4e8b44e801be6edbf138f284b202b55de4bfc4f29b8dd10f2bba0e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:02.765794Z","signature_b64":"MmXFTWZRDN9+MZJl+g+yTHTMzXmL+G1mLR/HS1AV3oeWwymcNqYDMKqOIbaSI/Y/jognQDlpaX+76Bw6f8RfAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"370fa92cafe59bc837617cdbc0ee9af8be765e56e967f91d57b221ca130317b4","last_reissued_at":"2026-05-17T23:50:02.765162Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:02.765162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Geometric Variational Approach to Bayesian Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Abhijoy Saha, Karthik Bharath, Sebastian Kurtek","submitted_at":"2017-07-31T03:59:00Z","abstract_excerpt":"We propose a novel Riemannian geometric framework for variational inference in Bayesian models based on the nonparametric Fisher-Rao metric on the manifold of probability density functions. Under the square-root density representation, the manifold can be identified with the positive orthant of the unit hypersphere in L2, and the Fisher-Rao metric reduces to the standard L2 metric. Exploiting such a Riemannian structure, we formulate the task of approximating the posterior distribution as a variational problem on the hypersphere based on the alpha-divergence. This provides a tighter lower boun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.09714","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":""},"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":"1707.09714","created_at":"2026-05-17T23:50:02.765249+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.09714v2","created_at":"2026-05-17T23:50:02.765249+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.09714","created_at":"2026-05-17T23:50:02.765249+00:00"},{"alias_kind":"pith_short_12","alias_value":"G4H2SLFP4WN4","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"G4H2SLFP4WN4QN3B","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"G4H2SLFP","created_at":"2026-05-18T12:31:15.632608+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/G4H2SLFP4WN4QN3BPTN4B3U27C","json":"https://pith.science/pith/G4H2SLFP4WN4QN3BPTN4B3U27C.json","graph_json":"https://pith.science/api/pith-number/G4H2SLFP4WN4QN3BPTN4B3U27C/graph.json","events_json":"https://pith.science/api/pith-number/G4H2SLFP4WN4QN3BPTN4B3U27C/events.json","paper":"https://pith.science/paper/G4H2SLFP"},"agent_actions":{"view_html":"https://pith.science/pith/G4H2SLFP4WN4QN3BPTN4B3U27C","download_json":"https://pith.science/pith/G4H2SLFP4WN4QN3BPTN4B3U27C.json","view_paper":"https://pith.science/paper/G4H2SLFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.09714&json=true","fetch_graph":"https://pith.science/api/pith-number/G4H2SLFP4WN4QN3BPTN4B3U27C/graph.json","fetch_events":"https://pith.science/api/pith-number/G4H2SLFP4WN4QN3BPTN4B3U27C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G4H2SLFP4WN4QN3BPTN4B3U27C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G4H2SLFP4WN4QN3BPTN4B3U27C/action/storage_attestation","attest_author":"https://pith.science/pith/G4H2SLFP4WN4QN3BPTN4B3U27C/action/author_attestation","sign_citation":"https://pith.science/pith/G4H2SLFP4WN4QN3BPTN4B3U27C/action/citation_signature","submit_replication":"https://pith.science/pith/G4H2SLFP4WN4QN3BPTN4B3U27C/action/replication_record"}},"created_at":"2026-05-17T23:50:02.765249+00:00","updated_at":"2026-05-17T23:50:02.765249+00:00"}