{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C5ABYLKSVKCCULCEWDQKE7HL6F","short_pith_number":"pith:C5ABYLKS","schema_version":"1.0","canonical_sha256":"17401c2d52aa842a2c44b0e0a27cebf15e4e67fad39345146f7751678a6447da","source":{"kind":"arxiv","id":"2405.12783","version":2},"attestation_state":"computed","paper":{"title":"On Kernel-based Variational Autoencoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Tian Qin, Wei-Min Huang","submitted_at":"2024-05-21T13:29:24Z","abstract_excerpt":"In this paper, we bridge Variational Autoencoders (VAEs) and kernel density estimations (KDEs) by approximating the posterior by KDEs and deriving an upper bound of the Kullback-Leibler (KL) divergence in the evidence lower bound (ELBO). The flexibility of KDEs makes the optimization of posteriors in VAEs possible, which not only addresses the limitations of Gaussian latent space in vanilla VAE but also provides a new perspective of estimating the KL-divergence in ELBO. Under appropriate conditions, we show that the Epanechnikov kernel is the optimal choice in minimizing the derived upper 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":"2405.12783","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-05-21T13:29:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"34df2f163cb1a65e4cbd2f8663a65043a899bf6c5456af9aa92372e870610a86","abstract_canon_sha256":"3689ead705b363de8cacfafb27597cbf524ae26b716e7b2010ac44290d3a9fcd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:24.614811Z","signature_b64":"zLnnFx0PjshhcSqCpCZWQ6nc+IZCUCo3BaP3cfY2jXxyDrt3nsRUHxKGYTgcS16wkZhple7prT8O5SoLJQv2Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17401c2d52aa842a2c44b0e0a27cebf15e4e67fad39345146f7751678a6447da","last_reissued_at":"2026-07-05T11:01:24.614307Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:24.614307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Kernel-based Variational Autoencoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Tian Qin, Wei-Min Huang","submitted_at":"2024-05-21T13:29:24Z","abstract_excerpt":"In this paper, we bridge Variational Autoencoders (VAEs) and kernel density estimations (KDEs) by approximating the posterior by KDEs and deriving an upper bound of the Kullback-Leibler (KL) divergence in the evidence lower bound (ELBO). The flexibility of KDEs makes the optimization of posteriors in VAEs possible, which not only addresses the limitations of Gaussian latent space in vanilla VAE but also provides a new perspective of estimating the KL-divergence in ELBO. Under appropriate conditions, we show that the Epanechnikov kernel is the optimal choice in minimizing the derived upper boun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12783","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.12783/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":"2405.12783","created_at":"2026-07-05T11:01:24.614380+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.12783v2","created_at":"2026-07-05T11:01:24.614380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12783","created_at":"2026-07-05T11:01:24.614380+00:00"},{"alias_kind":"pith_short_12","alias_value":"C5ABYLKSVKCC","created_at":"2026-07-05T11:01:24.614380+00:00"},{"alias_kind":"pith_short_16","alias_value":"C5ABYLKSVKCCULCE","created_at":"2026-07-05T11:01:24.614380+00:00"},{"alias_kind":"pith_short_8","alias_value":"C5ABYLKS","created_at":"2026-07-05T11:01:24.614380+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11824","citing_title":"REFNet++: Multi-Task Efficient Fusion of Camera and Radar Sensor Data in Bird's-Eye Polar View","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C5ABYLKSVKCCULCEWDQKE7HL6F","json":"https://pith.science/pith/C5ABYLKSVKCCULCEWDQKE7HL6F.json","graph_json":"https://pith.science/api/pith-number/C5ABYLKSVKCCULCEWDQKE7HL6F/graph.json","events_json":"https://pith.science/api/pith-number/C5ABYLKSVKCCULCEWDQKE7HL6F/events.json","paper":"https://pith.science/paper/C5ABYLKS"},"agent_actions":{"view_html":"https://pith.science/pith/C5ABYLKSVKCCULCEWDQKE7HL6F","download_json":"https://pith.science/pith/C5ABYLKSVKCCULCEWDQKE7HL6F.json","view_paper":"https://pith.science/paper/C5ABYLKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.12783&json=true","fetch_graph":"https://pith.science/api/pith-number/C5ABYLKSVKCCULCEWDQKE7HL6F/graph.json","fetch_events":"https://pith.science/api/pith-number/C5ABYLKSVKCCULCEWDQKE7HL6F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C5ABYLKSVKCCULCEWDQKE7HL6F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C5ABYLKSVKCCULCEWDQKE7HL6F/action/storage_attestation","attest_author":"https://pith.science/pith/C5ABYLKSVKCCULCEWDQKE7HL6F/action/author_attestation","sign_citation":"https://pith.science/pith/C5ABYLKSVKCCULCEWDQKE7HL6F/action/citation_signature","submit_replication":"https://pith.science/pith/C5ABYLKSVKCCULCEWDQKE7HL6F/action/replication_record"}},"created_at":"2026-07-05T11:01:24.614380+00:00","updated_at":"2026-07-05T11:01:24.614380+00:00"}