{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Y5FMBLOY6EERNWRZRLZPNSUGVQ","short_pith_number":"pith:Y5FMBLOY","schema_version":"1.0","canonical_sha256":"c74ac0add8f10916da398af2f6ca86ac057f1c15f4a5cb7a995b01f3d0cf548b","source":{"kind":"arxiv","id":"2312.09607","version":1},"attestation_state":"computed","paper":{"title":"Variational excess risk bound for general state space models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"stat.ME","authors_text":"\\'Elisabeth Gassiat (LM-Orsay), LPSM (UMR\\_8001)), Sylvain Le Corff (SU","submitted_at":"2023-12-15T08:41:07Z","abstract_excerpt":"In this paper, we consider variational autoencoders (VAE) for general state space models. We consider a backward factorization of the variational distributions to analyze the excess risk associated with VAE. Such backward factorizations were recently proposed to perform online variational learning  and to obtain upper bounds on the variational estimation error. When independent trajectories of sequences are observed and under strong mixing assumptions on the state space model and on the variational distribution, we provide an oracle inequality explicit in the number of samples and in the lengt"},"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":"2312.09607","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2023-12-15T08:41:07Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"30bc85829207772e41b43ba87c8dd63b01cc763f0698603a6708db09d0a74b16","abstract_canon_sha256":"7ac1a42c838b62d28372cc1ebae7ac0d2211e11479894be5858cfa025d02ece3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:28.008619Z","signature_b64":"vBjNnc3UZoKLC4QmfYpWd2tqDHLu4PO16/DtbDHxW4sYUzmSWGIrarTXo9dvYP+IUAdwctSwDzVE1fXyCld+Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c74ac0add8f10916da398af2f6ca86ac057f1c15f4a5cb7a995b01f3d0cf548b","last_reissued_at":"2026-07-05T07:24:28.008165Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:28.008165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational excess risk bound for general state space models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"stat.ME","authors_text":"\\'Elisabeth Gassiat (LM-Orsay), LPSM (UMR\\_8001)), Sylvain Le Corff (SU","submitted_at":"2023-12-15T08:41:07Z","abstract_excerpt":"In this paper, we consider variational autoencoders (VAE) for general state space models. We consider a backward factorization of the variational distributions to analyze the excess risk associated with VAE. Such backward factorizations were recently proposed to perform online variational learning  and to obtain upper bounds on the variational estimation error. When independent trajectories of sequences are observed and under strong mixing assumptions on the state space model and on the variational distribution, we provide an oracle inequality explicit in the number of samples and in the lengt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09607","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/2312.09607/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":"2312.09607","created_at":"2026-07-05T07:24:28.008220+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.09607v1","created_at":"2026-07-05T07:24:28.008220+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09607","created_at":"2026-07-05T07:24:28.008220+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y5FMBLOY6EER","created_at":"2026-07-05T07:24:28.008220+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y5FMBLOY6EERNWRZ","created_at":"2026-07-05T07:24:28.008220+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y5FMBLOY","created_at":"2026-07-05T07:24:28.008220+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/Y5FMBLOY6EERNWRZRLZPNSUGVQ","json":"https://pith.science/pith/Y5FMBLOY6EERNWRZRLZPNSUGVQ.json","graph_json":"https://pith.science/api/pith-number/Y5FMBLOY6EERNWRZRLZPNSUGVQ/graph.json","events_json":"https://pith.science/api/pith-number/Y5FMBLOY6EERNWRZRLZPNSUGVQ/events.json","paper":"https://pith.science/paper/Y5FMBLOY"},"agent_actions":{"view_html":"https://pith.science/pith/Y5FMBLOY6EERNWRZRLZPNSUGVQ","download_json":"https://pith.science/pith/Y5FMBLOY6EERNWRZRLZPNSUGVQ.json","view_paper":"https://pith.science/paper/Y5FMBLOY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.09607&json=true","fetch_graph":"https://pith.science/api/pith-number/Y5FMBLOY6EERNWRZRLZPNSUGVQ/graph.json","fetch_events":"https://pith.science/api/pith-number/Y5FMBLOY6EERNWRZRLZPNSUGVQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y5FMBLOY6EERNWRZRLZPNSUGVQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y5FMBLOY6EERNWRZRLZPNSUGVQ/action/storage_attestation","attest_author":"https://pith.science/pith/Y5FMBLOY6EERNWRZRLZPNSUGVQ/action/author_attestation","sign_citation":"https://pith.science/pith/Y5FMBLOY6EERNWRZRLZPNSUGVQ/action/citation_signature","submit_replication":"https://pith.science/pith/Y5FMBLOY6EERNWRZRLZPNSUGVQ/action/replication_record"}},"created_at":"2026-07-05T07:24:28.008220+00:00","updated_at":"2026-07-05T07:24:28.008220+00:00"}