{"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/infovae-information-maximizing-variational","title":"InfoVAE: Information Maximizing Variational Autoencoders","arxiv_id":"1706.02262","date":"2017-06-07","proceeding":null,"authors":["Shengjia Zhao","Jiaming Song","Stefano Ermon"],"abstract":"A key advance in learning generative models is the use of amortized inference\ndistributions that are jointly trained with the models. We find that existing\ntraining objectives for variational autoencoders can lead to inaccurate\namortized inference distributions and, in some cases, improving the objective\nprovably degrades the inference quality. In addition, it has been observed that\nvariational autoencoders tend to ignore the latent variables when combined with\na decoding distribution that is too flexible. We again identify the cause in\nexisting training criteria and propose a new class of objectives (InfoVAE) that\nmitigate these problems. We show that our model can significantly improve the\nquality of the variational posterior and can make effective use of the latent\nfeatures regardless of the flexibility of the decoding distribution. Through\nextensive qualitative and quantitative analyses, we demonstrate that our models\noutperform competing approaches on multiple performance metrics.","url_abs":"http://arxiv.org/abs/1706.02262v3","url_pdf":"http://arxiv.org/pdf/1706.02262v3.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":"infovae-information-maximizing-variational","repo_url":"https://github.com/AntixK/PyTorch-VAE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"infovae-information-maximizing-variational","repo_url":"https://github.com/Saswatm123/MMD-VAE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"infovae-information-maximizing-variational","repo_url":"https://github.com/clementchadebec/benchmark_VAE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"infovae-information-maximizing-variational","repo_url":"https://github.com/ema-marconato/glancenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"infovae-information-maximizing-variational","repo_url":"https://github.com/zacheberhart/Convolutional-Disentangled-Variational-Autoencoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"infovae-information-maximizing-variational","repo_url":"https://github.com/zacheberhart/Maximum-Mean-Discrepancy-Variational-Autoencoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.02262","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.02262"}},"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/AntixK/PyTorch-VAE","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ema-marconato/glancenet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/clementchadebec/benchmark_VAE","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zacheberhart/Convolutional-Disentangled-Variational-Autoencoder","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Saswatm123/MMD-VAE","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zacheberhart/Maximum-Mean-Discrepancy-Variational-Autoencoder","reach":{"status":"unanswered"}}],"summary":{"ran_draft_wrong":2,"ran_fixture":1},"by_repo_kind":{"listed":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"76cd8e24e234e5cb","entry":"compute_kernel","repo":"ema-marconato/glancenet","repo_kind":"listed","path":"models/infovae.py","file_url":"https://github.com/ema-marconato/glancenet/blob/HEAD/models/infovae.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"76cd8e24e234e5cb"}},{"code_sha256_prefix":"b1ebeb3cc68c188e","entry":"compute_mmd","repo":"ema-marconato/glancenet","repo_kind":"listed","path":"models/infovae.py","file_url":"https://github.com/ema-marconato/glancenet/blob/HEAD/models/infovae.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"b1ebeb3cc68c188e"}},{"code_sha256_prefix":"754708efc92cb9ad","entry":"infovae_loss_fn","repo":"ema-marconato/glancenet","repo_kind":"listed","path":"models/infovae.py","file_url":"https://github.com/ema-marconato/glancenet/blob/HEAD/models/infovae.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"754708efc92cb9ad"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}