{"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/learning-to-draw-samples-with-application-to","title":"Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Learning","arxiv_id":"1611.01722","date":"2016-11-06","proceeding":null,"authors":["Dilin Wang","Qiang Liu"],"abstract":"We propose a simple algorithm to train stochastic neural networks to draw\nsamples from given target distributions for probabilistic inference. Our method\nis based on iteratively adjusting the neural network parameters so that the\noutput changes along a Stein variational gradient that maximumly decreases the\nKL divergence with the target distribution. Our method works for any target\ndistribution specified by their unnormalized density function, and can train\nany black-box architectures that are differentiable in terms of the parameters\nwe want to adapt. As an application of our method, we propose an amortized MLE\nalgorithm for training deep energy model, where a neural sampler is adaptively\ntrained to approximate the likelihood function. Our method mimics an\nadversarial game between the deep energy model and the neural sampler, and\nobtains realistic-looking images competitive with the state-of-the-art results.","url_abs":"http://arxiv.org/abs/1611.01722v2","url_pdf":"http://arxiv.org/pdf/1611.01722v2.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":"learning-to-draw-samples-with-application-to","repo_url":"https://github.com/DartML/SteinGAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"conditional-image-generation","task_name":"Conditional Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/conditional-image-generation-on-cifar-10","task":"Conditional Image Generation","dataset":"CIFAR-10","model":"SteinGAN","rank_in_archive_order":25,"of":25,"metrics":{"Inception score":"6.35"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.01722","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.01722"}},"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/DartML/SteinGAN","reach":{"status":"ok","spdx":"MIT"}}],"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":"943324dfc9ef25a7","entry":"OneHot","repo":"DartML/SteinGAN","repo_kind":"official","path":"lib/data_utils.py","file_url":"https://github.com/DartML/SteinGAN/blob/HEAD/lib/data_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":"943324dfc9ef25a7"}},{"code_sha256_prefix":"4cf9776aa8ff3fbd","entry":"center_crop","repo":"DartML/SteinGAN","repo_kind":"official","path":"lib/data_utils.py","file_url":"https://github.com/DartML/SteinGAN/blob/HEAD/lib/data_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":"4cf9776aa8ff3fbd"}},{"code_sha256_prefix":"5bbf7febcf4fc287","entry":"intX","repo":"DartML/SteinGAN","repo_kind":"official","path":"lib/theano_utils.py","file_url":"https://github.com/DartML/SteinGAN/blob/HEAD/lib/theano_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":"5bbf7febcf4fc287"}},{"code_sha256_prefix":"6aca24795dd63a8b","entry":"min_resize","repo":"DartML/SteinGAN","repo_kind":"official","path":"lib/cv2_utils.py","file_url":"https://github.com/DartML/SteinGAN/blob/HEAD/lib/cv2_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":"6aca24795dd63a8b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}