{"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/inference-suboptimality-in-variational","title":"Inference Suboptimality in Variational Autoencoders","arxiv_id":"1801.03558","date":"2018-01-10","proceeding":"ICML 2018 7","authors":["Chris Cremer","Xuechen Li","David Duvenaud"],"abstract":"Amortized inference allows latent-variable models trained via variational\nlearning to scale to large datasets. The quality of approximate inference is\ndetermined by two factors: a) the capacity of the variational distribution to\nmatch the true posterior and b) the ability of the recognition network to\nproduce good variational parameters for each datapoint. We examine approximate\ninference in variational autoencoders in terms of these factors. We find that\ndivergence from the true posterior is often due to imperfect recognition\nnetworks, rather than the limited complexity of the approximating distribution.\nWe show that this is due partly to the generator learning to accommodate the\nchoice of approximation. Furthermore, we show that the parameters used to\nincrease the expressiveness of the approximation play a role in generalizing\ninference rather than simply improving the complexity of the approximation.","url_abs":"http://arxiv.org/abs/1801.03558v3","url_pdf":"http://arxiv.org/pdf/1801.03558v3.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":"inference-suboptimality-in-variational","repo_url":"https://github.com/chriscremer/Inference-Suboptimality","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"inference-suboptimality-in-variational","repo_url":"https://github.com/lxuechen/inference-suboptimality","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1801.03558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.03558"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/lxuechen/inference-suboptimality","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chriscremer/Inference-Suboptimality","reach":null}],"summary":{"ran_honours":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"715241df022a8fa7","entry":"load_mnist","repo":"chriscremer/Inference-Suboptimality","repo_kind":"official","path":"gaps_over_training_exp/compute_gaps.py","file_url":"https://github.com/chriscremer/Inference-Suboptimality/blob/HEAD/gaps_over_training_exp/compute_gaps.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"715241df022a8fa7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}