{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OXKI263YDPPIOVG2ENFUXM2FPJ","short_pith_number":"pith:OXKI263Y","schema_version":"1.0","canonical_sha256":"75d48d7b781bde8754da234b4bb3457a7f0692fd1f42779f93d2e9f88625d966","source":{"kind":"arxiv","id":"1802.06847","version":4},"attestation_state":"computed","paper":{"title":"Distribution Matching in Variational Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Balaji Lakshminarayanan, Mihaela Rosca, Shakir Mohamed","submitted_at":"2018-02-19T20:59:33Z","abstract_excerpt":"With the increasingly widespread deployment of generative models, there is a mounting need for a deeper understanding of their behaviors and limitations. In this paper, we expose the limitations of Variational Autoencoders (VAEs), which consistently fail to learn marginal distributions in both latent and visible spaces. We show this to be a consequence of learning by matching conditional distributions, and the limitations of explicit model and posterior distributions. It is popular to consider Generative Adversarial Networks (GANs) as a means of overcoming these limitations, leading to hybrids"},"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":"1802.06847","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-19T20:59:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"06ecc7b61564340718e23ae4f14eb9936b3d5d66b0a7eaf2af85a96c1bbfd3a8","abstract_canon_sha256":"6a23c932375e9b6b057aad49b907c95a67879597d9a8b4211706399ba74a05f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:43.297139Z","signature_b64":"UXSv1LMmcrPCo1j7c7qSkHt+Wh+99vx2CnpuaLw6CXVp8Pj5UkbkHRJ3UBfDs4vZTNjkJRyzafnb2eJyPZufDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75d48d7b781bde8754da234b4bb3457a7f0692fd1f42779f93d2e9f88625d966","last_reissued_at":"2026-05-17T23:43:43.296533Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:43.296533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distribution Matching in Variational Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Balaji Lakshminarayanan, Mihaela Rosca, Shakir Mohamed","submitted_at":"2018-02-19T20:59:33Z","abstract_excerpt":"With the increasingly widespread deployment of generative models, there is a mounting need for a deeper understanding of their behaviors and limitations. In this paper, we expose the limitations of Variational Autoencoders (VAEs), which consistently fail to learn marginal distributions in both latent and visible spaces. We show this to be a consequence of learning by matching conditional distributions, and the limitations of explicit model and posterior distributions. It is popular to consider Generative Adversarial Networks (GANs) as a means of overcoming these limitations, leading to hybrids"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06847","kind":"arxiv","version":4},"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":"1802.06847","created_at":"2026-05-17T23:43:43.296638+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.06847v4","created_at":"2026-05-17T23:43:43.296638+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06847","created_at":"2026-05-17T23:43:43.296638+00:00"},{"alias_kind":"pith_short_12","alias_value":"OXKI263YDPPI","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OXKI263YDPPIOVG2","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OXKI263Y","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2602.15451","citing_title":"Molecular Design beyond Training Data with Novel Extended Objective Functionals of Generative AI Models Driven by Quantum Annealing Computer","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OXKI263YDPPIOVG2ENFUXM2FPJ","json":"https://pith.science/pith/OXKI263YDPPIOVG2ENFUXM2FPJ.json","graph_json":"https://pith.science/api/pith-number/OXKI263YDPPIOVG2ENFUXM2FPJ/graph.json","events_json":"https://pith.science/api/pith-number/OXKI263YDPPIOVG2ENFUXM2FPJ/events.json","paper":"https://pith.science/paper/OXKI263Y"},"agent_actions":{"view_html":"https://pith.science/pith/OXKI263YDPPIOVG2ENFUXM2FPJ","download_json":"https://pith.science/pith/OXKI263YDPPIOVG2ENFUXM2FPJ.json","view_paper":"https://pith.science/paper/OXKI263Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.06847&json=true","fetch_graph":"https://pith.science/api/pith-number/OXKI263YDPPIOVG2ENFUXM2FPJ/graph.json","fetch_events":"https://pith.science/api/pith-number/OXKI263YDPPIOVG2ENFUXM2FPJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OXKI263YDPPIOVG2ENFUXM2FPJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OXKI263YDPPIOVG2ENFUXM2FPJ/action/storage_attestation","attest_author":"https://pith.science/pith/OXKI263YDPPIOVG2ENFUXM2FPJ/action/author_attestation","sign_citation":"https://pith.science/pith/OXKI263YDPPIOVG2ENFUXM2FPJ/action/citation_signature","submit_replication":"https://pith.science/pith/OXKI263YDPPIOVG2ENFUXM2FPJ/action/replication_record"}},"created_at":"2026-05-17T23:43:43.296638+00:00","updated_at":"2026-05-17T23:43:43.296638+00:00"}