{"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/on-the-quantitative-analysis-of-decoder-based","title":"On the Quantitative Analysis of Decoder-Based Generative Models","arxiv_id":"1611.04273","date":"2016-11-14","proceeding":null,"authors":["Yuhuai Wu","Yuri Burda","Ruslan Salakhutdinov","Roger Grosse"],"abstract":"The past several years have seen remarkable progress in generative models\nwhich produce convincing samples of images and other modalities. A shared\ncomponent of many powerful generative models is a decoder network, a parametric\ndeep neural net that defines a generative distribution. Examples include\nvariational autoencoders, generative adversarial networks, and generative\nmoment matching networks. Unfortunately, it can be difficult to quantify the\nperformance of these models because of the intractability of log-likelihood\nestimation, and inspecting samples can be misleading. We propose to use\nAnnealed Importance Sampling for evaluating log-likelihoods for decoder-based\nmodels and validate its accuracy using bidirectional Monte Carlo. The\nevaluation code is provided at https://github.com/tonywu95/eval_gen. Using this\ntechnique, we analyze the performance of decoder-based models, the\neffectiveness of existing log-likelihood estimators, the degree of overfitting,\nand the degree to which these models miss important modes of the data\ndistribution.","url_abs":"http://arxiv.org/abs/1611.04273v2","url_pdf":"http://arxiv.org/pdf/1611.04273v2.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":"on-the-quantitative-analysis-of-decoder-based","repo_url":"https://github.com/tonywu95/eval_gen","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"on-the-quantitative-analysis-of-decoder-based","repo_url":"https://github.com/jiamings/ais","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.04273","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.04273"}},"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/jiamings/ais","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tonywu95/eval_gen","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"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":0,"samples":[{"code_sha256_prefix":"548b0453da6dc726","entry":"load_simulated","repo":"tonywu95/eval_gen","repo_kind":"official","path":"lib/utils.py","file_url":"https://github.com/tonywu95/eval_gen/blob/HEAD/lib/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"548b0453da6dc726"}},{"code_sha256_prefix":"ea7028bf46213455","entry":"fixbinary_mnist","repo":"tonywu95/eval_gen","repo_kind":"official","path":"lib/utils.py","file_url":"https://github.com/tonywu95/eval_gen/blob/HEAD/lib/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ea7028bf46213455"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}