{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TW5NUXBNQHNW5PQV2K3TS3GE7A","short_pith_number":"pith:TW5NUXBN","schema_version":"1.0","canonical_sha256":"9dbada5c2d81db6ebe15d2b7396cc4f82bd1eb06be048cab7f7e3a18ec1c031c","source":{"kind":"arxiv","id":"1810.01118","version":3},"attestation_state":"computed","paper":{"title":"Sinkhorn AutoEncoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Frank Nielsen, Giorgio Patrini, Marcello Carioni, Max Welling, Patrick Forr\\'e, Rianne van den Berg, Samarth Bhargav, Tim Genewein","submitted_at":"2018-10-02T08:43:08Z","abstract_excerpt":"Optimal transport offers an alternative to maximum likelihood for learning generative autoencoding models. We show that minimizing the p-Wasserstein distance between the generator and the true data distribution is equivalent to the unconstrained min-min optimization of the p-Wasserstein distance between the encoder aggregated posterior and the prior in latent space, plus a reconstruction error. We also identify the role of its trade-off hyperparameter as the capacity of the generator: its Lipschitz constant. Moreover, we prove that optimizing the encoder over any class of universal approximato"},"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":"1810.01118","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-02T08:43:08Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"7087df552b3bdbbec21bde0f95bee90f66f87e21c46d1108f2e8a908fd10dc5e","abstract_canon_sha256":"ad94e0096d9d2d9cc310485f97bf2bb7a66e8b23ec750d68761277d26185a1c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:34.339333Z","signature_b64":"LJv13f9sNxly5gwumFywdPlzrN0GEysxeeueYHUAbZmwmIPlY+DYpMARdRfCXZ7ZDuWAdrdlLMWhieRyuAhBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dbada5c2d81db6ebe15d2b7396cc4f82bd1eb06be048cab7f7e3a18ec1c031c","last_reissued_at":"2026-05-17T23:40:34.338750Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:34.338750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sinkhorn AutoEncoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Frank Nielsen, Giorgio Patrini, Marcello Carioni, Max Welling, Patrick Forr\\'e, Rianne van den Berg, Samarth Bhargav, Tim Genewein","submitted_at":"2018-10-02T08:43:08Z","abstract_excerpt":"Optimal transport offers an alternative to maximum likelihood for learning generative autoencoding models. We show that minimizing the p-Wasserstein distance between the generator and the true data distribution is equivalent to the unconstrained min-min optimization of the p-Wasserstein distance between the encoder aggregated posterior and the prior in latent space, plus a reconstruction error. We also identify the role of its trade-off hyperparameter as the capacity of the generator: its Lipschitz constant. Moreover, we prove that optimizing the encoder over any class of universal approximato"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.01118","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":""},"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":"1810.01118","created_at":"2026-05-17T23:40:34.338849+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.01118v3","created_at":"2026-05-17T23:40:34.338849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.01118","created_at":"2026-05-17T23:40:34.338849+00:00"},{"alias_kind":"pith_short_12","alias_value":"TW5NUXBNQHNW","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"TW5NUXBNQHNW5PQV","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"TW5NUXBN","created_at":"2026-05-18T12:32:56.356000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.04050","citing_title":"k-GANs: Ensemble of Generative Models with Semi-Discrete Optimal Transport","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TW5NUXBNQHNW5PQV2K3TS3GE7A","json":"https://pith.science/pith/TW5NUXBNQHNW5PQV2K3TS3GE7A.json","graph_json":"https://pith.science/api/pith-number/TW5NUXBNQHNW5PQV2K3TS3GE7A/graph.json","events_json":"https://pith.science/api/pith-number/TW5NUXBNQHNW5PQV2K3TS3GE7A/events.json","paper":"https://pith.science/paper/TW5NUXBN"},"agent_actions":{"view_html":"https://pith.science/pith/TW5NUXBNQHNW5PQV2K3TS3GE7A","download_json":"https://pith.science/pith/TW5NUXBNQHNW5PQV2K3TS3GE7A.json","view_paper":"https://pith.science/paper/TW5NUXBN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.01118&json=true","fetch_graph":"https://pith.science/api/pith-number/TW5NUXBNQHNW5PQV2K3TS3GE7A/graph.json","fetch_events":"https://pith.science/api/pith-number/TW5NUXBNQHNW5PQV2K3TS3GE7A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TW5NUXBNQHNW5PQV2K3TS3GE7A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TW5NUXBNQHNW5PQV2K3TS3GE7A/action/storage_attestation","attest_author":"https://pith.science/pith/TW5NUXBNQHNW5PQV2K3TS3GE7A/action/author_attestation","sign_citation":"https://pith.science/pith/TW5NUXBNQHNW5PQV2K3TS3GE7A/action/citation_signature","submit_replication":"https://pith.science/pith/TW5NUXBNQHNW5PQV2K3TS3GE7A/action/replication_record"}},"created_at":"2026-05-17T23:40:34.338849+00:00","updated_at":"2026-05-17T23:40:34.338849+00:00"}