{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/dataset-size-dependence-of-rate-distortion","title":"High-dimensional Asymptotics of VAEs: Threshold of Posterior Collapse and Dataset-Size Dependence of Rate-Distortion Curve","arxiv_id":"2309.07663","date":"2023-09-14","proceeding":null,"authors":["Yuma Ichikawa","Koji Hukushima"],"abstract":"In variational autoencoders (VAEs), the variational posterior often collapses to the prior, known as posterior collapse, which leads to poor representation learning quality. An adjustable hyperparameter beta has been introduced in VAEs to address this issue. This study sharply evaluates the conditions under which the posterior collapse occurs with respect to beta and dataset size by analyzing a minimal VAE in a high-dimensional limit. Additionally, this setting enables the evaluation of the rate-distortion curve of the VAE. Our results show that, unlike typical regularization parameters, VAEs face \"inevitable posterior collapse\" beyond a certain beta threshold, regardless of dataset size. Moreover, the dataset-size dependence of the derived rate-distortion curve suggests that relatively large datasets are required to achieve a rate-distortion curve with high rates. These findings robustly explain generalization behavior observed in various real datasets with highly non-linear VAEs.","url_abs":"https://arxiv.org/abs/2309.07663v2","url_pdf":"https://arxiv.org/pdf/2309.07663v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"dataset-size-dependence-of-rate-distortion","repo_url":"https://github.com/yuma-ichikawa/vae-replica","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2309.07663","atlas_url":"https://app.syntology.ai/?focus=2309.07663","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07663"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yuma-ichikawa/vae-replica","reach":null}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"33e8ef13d600b950","entry":"criterion","repo":"yuma-ichikawa/vae-replica","repo_kind":"official","path":"src/vae.py","file_url":"https://github.com/yuma-ichikawa/vae-replica/blob/HEAD/src/vae.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause-Clear","inline_ok":false,"mcp_get_code":{"code_sha256":"33e8ef13d600b950"}},{"code_sha256_prefix":"c5561208aaa51bae","entry":"criterion_for1rank","repo":"yuma-ichikawa/vae-replica","repo_kind":"official","path":"src/vae.py","file_url":"https://github.com/yuma-ichikawa/vae-replica/blob/HEAD/src/vae.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause-Clear","inline_ok":false,"mcp_get_code":{"code_sha256":"c5561208aaa51bae"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}