{"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/amortized-population-gibbs-samplers-with","title":"Amortized Population Gibbs Samplers with Neural Sufficient Statistics","arxiv_id":"1911.01382","date":"2019-11-04","proceeding":"ICML 2020 1","authors":["Hao Wu","Heiko Zimmermann","Eli Sennesh","Tuan Anh Le","Jan-Willem van de Meent"],"abstract":"We develop amortized population Gibbs (APG) samplers, a class of scalable methods that frames structured variational inference as adaptive importance sampling. APG samplers construct high-dimensional proposals by iterating over updates to lower-dimensional blocks of variables. We train each conditional proposal by minimizing the inclusive KL divergence with respect to the conditional posterior. To appropriately account for the size of the input data, we develop a new parameterization in terms of neural sufficient statistics. Experiments show that APG samplers can train highly structured deep generative models in an unsupervised manner, and achieve substantial improvements in inference accuracy relative to standard autoencoding variational methods.","url_abs":"https://arxiv.org/abs/1911.01382v3","url_pdf":"https://arxiv.org/pdf/1911.01382v3.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":"amortized-population-gibbs-samplers-with","repo_url":"https://github.com/hao-w/apg-samplers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1911.01382","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.01382"}},"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/hao-w/apg-samplers","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":5},"by_repo_kind":{"listed":{"samples":5,"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":"8e09376d898efa04","entry":"MBern_log_prob","repo":"hao-w/apg-samplers","repo_kind":"listed","path":"apgs/bmnist/models.py","file_url":"https://github.com/hao-w/apg-samplers/blob/HEAD/apgs/bmnist/models.py","link_basis":"harvester_set","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":"8e09376d898efa04"}},{"code_sha256_prefix":"ad0adffe0bda411b","entry":"apg_objective","repo":"hao-w/apg-samplers","repo_kind":"listed","path":"apgs/bmnist/objectives.py","file_url":"https://github.com/hao-w/apg-samplers/blob/HEAD/apgs/bmnist/objectives.py","link_basis":"harvester_set","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":"ad0adffe0bda411b"}},{"code_sha256_prefix":"07f6c1d22892e3ec","entry":"propose_one_movement","repo":"hao-w/apg-samplers","repo_kind":"listed","path":"apgs/bmnist/objectives.py","file_url":"https://github.com/hao-w/apg-samplers/blob/HEAD/apgs/bmnist/objectives.py","link_basis":"harvester_set","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":"07f6c1d22892e3ec"}},{"code_sha256_prefix":"db4f86d76a6c6372","entry":"resample_variables","repo":"hao-w/apg-samplers","repo_kind":"listed","path":"apgs/bmnist/objectives.py","file_url":"https://github.com/hao-w/apg-samplers/blob/HEAD/apgs/bmnist/objectives.py","link_basis":"harvester_set","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":"db4f86d76a6c6372"}},{"code_sha256_prefix":"cd23d890a42f8c16","entry":"shuffler","repo":"hao-w/apg-samplers","repo_kind":"listed","path":"apgs/dmm/apg_training.py","file_url":"https://github.com/hao-w/apg-samplers/blob/HEAD/apgs/dmm/apg_training.py","link_basis":"harvester_set","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":"cd23d890a42f8c16"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}