{"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","title":"Iterative Neural Autoregressive Distribution Estimator NADE-k","arxiv_id":null,"date":"2014-12-01","proceeding":"NeurIPS 2014 12","authors":["Tapani Raiko","Yao Li","Kyunghyun Cho","Yoshua Bengio"],"abstract":"Training of the neural autoregressive density estimator (NADE) can be viewed as doing one step of probabilistic inference on missing values in data. We propose a new model that extends this inference scheme to multiple steps, arguing that it is easier to learn to improve a reconstruction in $k$ steps rather than to learn to reconstruct in a single inference step. The proposed model is an unsupervised building block for deep learning that combines the desirable properties of NADE and multi-predictive training: (1) Its test likelihood can be computed analytically, (2) it is easy to generate independent samples from it, and (3) it uses an inference engine that is a superset of variational inference for Boltzmann machines. The proposed NADE-k is competitive with the state-of-the-art in density estimation on the two datasets tested.","url_abs":"http://papers.nips.cc/paper/5277-iterative-neural-autoregressive-distribution-estimator-nade-k","url_pdf":"http://papers.nips.cc/paper/5277-iterative-neural-autoregressive-distribution-estimator-nade-k.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","repo_url":"https://github.com/yaoli/nade_k","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"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 2hl (128 orders)","rank_in_archive_order":8,"of":10,"metrics":{"nats":"85.10"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}