{"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/joint-stochastic-approximation-and-its","title":"Joint Stochastic Approximation and Its Application to Learning Discrete Latent Variable Models","arxiv_id":"2005.14001","date":"2020-05-28","proceeding":null,"authors":["Zhijian Ou","Yunfu Song"],"abstract":"Although with progress in introducing auxiliary amortized inference models, learning discrete latent variable models is still challenging. In this paper, we show that the annoying difficulty of obtaining reliable stochastic gradients for the inference model and the drawback of indirectly optimizing the target log-likelihood can be gracefully addressed in a new method based on stochastic approximation (SA) theory of the Robbins-Monro type. Specifically, we propose to directly maximize the target log-likelihood and simultaneously minimize the inclusive divergence between the posterior and the inference model. The resulting learning algorithm is called joint SA (JSA). To the best of our knowledge, JSA represents the first method that couples an SA version of the EM (expectation-maximization) algorithm (SAEM) with an adaptive MCMC procedure. Experiments on several benchmark generative modeling and structured prediction tasks show that JSA consistently outperforms recent competitive algorithms, with faster convergence, better final likelihoods, and lower variance of gradient estimates.","url_abs":"https://arxiv.org/abs/2005.14001v1","url_pdf":"https://arxiv.org/pdf/2005.14001v1.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":"joint-stochastic-approximation-and-its","repo_url":"https://github.com/thu-spmi/JSA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"structured-prediction","task_name":"Structured Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2005.14001","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14001"}},"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/thu-spmi/JSA","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"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":"da7f96d425f86042","entry":"bernoulli_loglikelihood","repo":"thu-spmi/JSA","repo_kind":"official","path":"categorical_MNIST/jsa.py","file_url":"https://github.com/thu-spmi/JSA/blob/HEAD/categorical_MNIST/jsa.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"da7f96d425f86042"}},{"code_sha256_prefix":"77500742f3d04cef","entry":"categorical_loglikelihood","repo":"thu-spmi/JSA","repo_kind":"official","path":"categorical_MNIST/jsa.py","file_url":"https://github.com/thu-spmi/JSA/blob/HEAD/categorical_MNIST/jsa.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"77500742f3d04cef"}},{"code_sha256_prefix":"93e36cce9edd7cfb","entry":"datapath","repo":"thu-spmi/JSA","repo_kind":"official","path":"bernoulli_MNIST/mnist.py","file_url":"https://github.com/thu-spmi/JSA/blob/HEAD/bernoulli_MNIST/mnist.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"93e36cce9edd7cfb"}},{"code_sha256_prefix":"8deea25eec5485cb","entry":"repeat","repo":"thu-spmi/JSA","repo_kind":"official","path":"bernoulli_MNIST/linear_model.py","file_url":"https://github.com/thu-spmi/JSA/blob/HEAD/bernoulli_MNIST/linear_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8deea25eec5485cb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}