{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2DOLBBHYYHTO7IILHFLDI7GHZY","short_pith_number":"pith:2DOLBBHY","schema_version":"1.0","canonical_sha256":"d0dcb084f8c1e6efa10b3956347cc7ce256bb759e9f615840c68de14dd8b792e","source":{"kind":"arxiv","id":"2306.13520","version":1},"attestation_state":"computed","paper":{"title":"On the Convergence Rate of Gaussianization with Random Rotations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Armand Rousselot, Christoph Schn\\\"orr, Felix Draxler, Jens M\\\"uller, Lars K\\\"uhmichel, Ullrich K\\\"othe","submitted_at":"2023-06-23T14:35:39Z","abstract_excerpt":"Gaussianization is a simple generative model that can be trained without backpropagation. It has shown compelling performance on low dimensional data. As the dimension increases, however, it has been observed that the convergence speed slows down. We show analytically that the number of required layers scales linearly with the dimension for Gaussian input. We argue that this is because the model is unable to capture dependencies between dimensions. Empirically, we find the same linear increase in cost for arbitrary input $p(x)$, but observe favorable scaling for some distributions. We explore "},"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":"2306.13520","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-23T14:35:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0f1e273c01d9975693e0fa6a8658e42ac161ee575fb02bc834f499f1bf420674","abstract_canon_sha256":"06b8c3b0d81f4edd6013e7b9621ce484e497b0e1e335b98ad46a3142db40ba2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:06.436928Z","signature_b64":"lKKbjfbcW1QDUwMysfuJKO43smUEu262xC5iyTi78e5GCbTlKokqw3/veM/EgwcFvDR0OvWekRp0dWxHUpI3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0dcb084f8c1e6efa10b3956347cc7ce256bb759e9f615840c68de14dd8b792e","last_reissued_at":"2026-07-05T06:24:06.436554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:06.436554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Convergence Rate of Gaussianization with Random Rotations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Armand Rousselot, Christoph Schn\\\"orr, Felix Draxler, Jens M\\\"uller, Lars K\\\"uhmichel, Ullrich K\\\"othe","submitted_at":"2023-06-23T14:35:39Z","abstract_excerpt":"Gaussianization is a simple generative model that can be trained without backpropagation. It has shown compelling performance on low dimensional data. As the dimension increases, however, it has been observed that the convergence speed slows down. We show analytically that the number of required layers scales linearly with the dimension for Gaussian input. We argue that this is because the model is unable to capture dependencies between dimensions. Empirically, we find the same linear increase in cost for arbitrary input $p(x)$, but observe favorable scaling for some distributions. We explore "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.13520","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/2306.13520/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":"2306.13520","created_at":"2026-07-05T06:24:06.436613+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.13520v1","created_at":"2026-07-05T06:24:06.436613+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.13520","created_at":"2026-07-05T06:24:06.436613+00:00"},{"alias_kind":"pith_short_12","alias_value":"2DOLBBHYYHTO","created_at":"2026-07-05T06:24:06.436613+00:00"},{"alias_kind":"pith_short_16","alias_value":"2DOLBBHYYHTO7IIL","created_at":"2026-07-05T06:24:06.436613+00:00"},{"alias_kind":"pith_short_8","alias_value":"2DOLBBHY","created_at":"2026-07-05T06:24:06.436613+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/2DOLBBHYYHTO7IILHFLDI7GHZY","json":"https://pith.science/pith/2DOLBBHYYHTO7IILHFLDI7GHZY.json","graph_json":"https://pith.science/api/pith-number/2DOLBBHYYHTO7IILHFLDI7GHZY/graph.json","events_json":"https://pith.science/api/pith-number/2DOLBBHYYHTO7IILHFLDI7GHZY/events.json","paper":"https://pith.science/paper/2DOLBBHY"},"agent_actions":{"view_html":"https://pith.science/pith/2DOLBBHYYHTO7IILHFLDI7GHZY","download_json":"https://pith.science/pith/2DOLBBHYYHTO7IILHFLDI7GHZY.json","view_paper":"https://pith.science/paper/2DOLBBHY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.13520&json=true","fetch_graph":"https://pith.science/api/pith-number/2DOLBBHYYHTO7IILHFLDI7GHZY/graph.json","fetch_events":"https://pith.science/api/pith-number/2DOLBBHYYHTO7IILHFLDI7GHZY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2DOLBBHYYHTO7IILHFLDI7GHZY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2DOLBBHYYHTO7IILHFLDI7GHZY/action/storage_attestation","attest_author":"https://pith.science/pith/2DOLBBHYYHTO7IILHFLDI7GHZY/action/author_attestation","sign_citation":"https://pith.science/pith/2DOLBBHYYHTO7IILHFLDI7GHZY/action/citation_signature","submit_replication":"https://pith.science/pith/2DOLBBHYYHTO7IILHFLDI7GHZY/action/replication_record"}},"created_at":"2026-07-05T06:24:06.436613+00:00","updated_at":"2026-07-05T06:24:06.436613+00:00"}