{"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/autoregressive-energy-machines","title":"Autoregressive Energy Machines","arxiv_id":"1904.05626","date":"2019-04-11","proceeding":null,"authors":["Charlie Nash","Conor Durkan"],"abstract":"Neural density estimators are flexible families of parametric models which\nhave seen widespread use in unsupervised machine learning in recent years.\nMaximum-likelihood training typically dictates that these models be constrained\nto specify an explicit density. However, this limitation can be overcome by\ninstead using a neural network to specify an energy function, or unnormalized\ndensity, which can subsequently be normalized to obtain a valid distribution.\nThe challenge with this approach lies in accurately estimating the normalizing\nconstant of the high-dimensional energy function. We propose the Autoregressive\nEnergy Machine, an energy-based model which simultaneously learns an\nunnormalized density and computes an importance-sampling estimate of the\nnormalizing constant for each conditional in an autoregressive decomposition.\nThe Autoregressive Energy Machine achieves state-of-the-art performance on a\nsuite of density-estimation tasks.","url_abs":"http://arxiv.org/abs/1904.05626v1","url_pdf":"http://arxiv.org/pdf/1904.05626v1.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":"autoregressive-energy-machines","repo_url":"https://github.com/conormdurkan/autoregressive-energy-machines","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"density-estimation","task_name":"Density Estimation"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.05626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.05626"}},"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/conormdurkan/autoregressive-energy-machines","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"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":"6bedc2b0d140cfa2","entry":"contextual_res_net","repo":"conormdurkan/autoregressive-energy-machines","repo_kind":"official","path":"tensorflow/utils/energy_nets.py","file_url":"https://github.com/conormdurkan/autoregressive-energy-machines/blob/HEAD/tensorflow/utils/energy_nets.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":"6bedc2b0d140cfa2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}