{"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/deep-energy-estimator-networks","title":"Deep Energy Estimator Networks","arxiv_id":"1805.08306","date":"2018-05-21","proceeding":null,"authors":["Saeed Saremi","Arash Mehrjou","Bernhard Schölkopf","Aapo Hyvärinen"],"abstract":"Density estimation is a fundamental problem in statistical learning. This\nproblem is especially challenging for complex high-dimensional data due to the\ncurse of dimensionality. A promising solution to this problem is given here in\nan inference-free hierarchical framework that is built on score matching. We\nrevisit the Bayesian interpretation of the score function and the Parzen score\nmatching, and construct a multilayer perceptron with a scalable objective for\nlearning the energy (i.e. the unnormalized log-density), which is then\noptimized with stochastic gradient descent. In addition, the resulting deep\nenergy estimator network (DEEN) is designed as products of experts. We present\nthe utility of DEEN in learning the energy, the score function, and in\nsingle-step denoising experiments for synthetic and high-dimensional data. We\nalso diagnose stability problems in the direct estimation of the score function\nthat had been observed for denoising autoencoders.","url_abs":"http://arxiv.org/abs/1805.08306v1","url_pdf":"http://arxiv.org/pdf/1805.08306v1.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":"deep-energy-estimator-networks","repo_url":"https://github.com/Ending2015a/toy_gradlogp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"density-estimation","task_name":"Density Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.08306","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}