{"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/langevin-autoencoders-for-learning-deep-1","title":"Langevin Autoencoders for Learning Deep Latent Variable Models","arxiv_id":"2209.07036","date":"2022-09-15","proceeding":null,"authors":["Shohei Taniguchi","Yusuke Iwasawa","Wataru Kumagai","Yutaka Matsuo"],"abstract":"Markov chain Monte Carlo (MCMC), such as Langevin dynamics, is valid for approximating intractable distributions. However, its usage is limited in the context of deep latent variable models owing to costly datapoint-wise sampling iterations and slow convergence. This paper proposes the amortized Langevin dynamics (ALD), wherein datapoint-wise MCMC iterations are entirely replaced with updates of an encoder that maps observations into latent variables. This amortization enables efficient posterior sampling without datapoint-wise iterations. Despite its efficiency, we prove that ALD is valid as an MCMC algorithm, whose Markov chain has the target posterior as a stationary distribution under mild assumptions. Based on the ALD, we also present a new deep latent variable model named the Langevin autoencoder (LAE). Interestingly, the LAE can be implemented by slightly modifying the traditional autoencoder. Using multiple synthetic datasets, we first validate that ALD can properly obtain samples from target posteriors. We also evaluate the LAE on the image generation task, and show that our LAE can outperform existing methods based on variational inference, such as the variational autoencoder, and other MCMC-based methods in terms of the test likelihood.","url_abs":"https://arxiv.org/abs/2209.07036v2","url_pdf":"https://arxiv.org/pdf/2209.07036v2.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":"langevin-autoencoders-for-learning-deep-1","repo_url":"https://github.com/ishohei220/lae","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"variational-inference","task_name":"Variational Inference"},{"task_slug":null,"task_name":"valid"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2209.07036","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.07036"}},"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":"deterministic:regex_extraction","url":"https://github.com/iShohei220/LAE","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ishohei220/lae","reach":{"status":"ok"}}],"summary":{"ran":2,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":5,"samples":[{"code_sha256_prefix":"5aa78eb2075a5c49","entry":"Decoder","repo":"ishohei220/lae","repo_kind":"official","path":"model.py","file_url":"https://github.com/ishohei220/lae/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5aa78eb2075a5c49"}},{"code_sha256_prefix":"4fa0baeae9aaeb96","entry":"Encoder","repo":"ishohei220/lae","repo_kind":"official","path":"model.py","file_url":"https://github.com/ishohei220/lae/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4fa0baeae9aaeb96"}},{"code_sha256_prefix":"6f6bc7078f9d1761","entry":"discretized_logistic_energy","repo":"ishohei220/lae","repo_kind":"official","path":"model.py","file_url":"https://github.com/ishohei220/lae/blob/HEAD/model.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6f6bc7078f9d1761"}},{"code_sha256_prefix":"c566137298fe478e","entry":"discretized_logistic_energy","repo":"ishohei220/lae","repo_kind":"official","path":"model.py","file_url":"https://github.com/ishohei220/lae/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c566137298fe478e"}},{"code_sha256_prefix":"e0afdb70fa73e9c0","entry":"LAE","repo":"ishohei220/lae","repo_kind":"official","path":"model.py","file_url":"https://github.com/ishohei220/lae/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e0afdb70fa73e9c0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}