{"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/iterative-neural-autoregressive-distribution-1","title":"Iterative Neural Autoregressive Distribution Estimator (NADE-k)","arxiv_id":"1406.1485","date":"2014-06-05","proceeding":null,"authors":["Tapani Raiko","Li Yao","Kyunghyun Cho","Yoshua Bengio"],"abstract":"Training of the neural autoregressive density estimator (NADE) can be viewed\nas doing one step of probabilistic inference on missing values in data. We\npropose a new model that extends this inference scheme to multiple steps,\narguing that it is easier to learn to improve a reconstruction in $k$ steps\nrather than to learn to reconstruct in a single inference step. The proposed\nmodel is an unsupervised building block for deep learning that combines the\ndesirable properties of NADE and multi-predictive training: (1) Its test\nlikelihood can be computed analytically, (2) it is easy to generate independent\nsamples from it, and (3) it uses an inference engine that is a superset of\nvariational inference for Boltzmann machines. The proposed NADE-k is\ncompetitive with the state-of-the-art in density estimation on the two datasets\ntested.","url_abs":"http://arxiv.org/abs/1406.1485v3","url_pdf":"http://arxiv.org/pdf/1406.1485v3.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":"iterative-neural-autoregressive-distribution-1","repo_url":"https://github.com/yaoli/nade_k","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"density-estimation","task_name":"Density Estimation"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"missing-values","task_name":"Missing Values"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-binarized-mnist","task":"Image Generation","dataset":"Binarized MNIST","model":"EoNADE-5 2hl (128 orders)","rank_in_archive_order":7,"of":10,"metrics":{"nats":"84.68"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1406.1485","atlas_url":"https://app.syntology.ai/?focus=1406.1485","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}