{"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/improving-sampling-from-generative","title":"Improving Sampling from Generative Autoencoders with Markov Chains","arxiv_id":"1610.09296","date":"2016-10-28","proceeding":null,"authors":["Antonia Creswell","Kai Arulkumaran","Anil Anthony Bharath"],"abstract":"We focus on generative autoencoders, such as variational or adversarial\nautoencoders, which jointly learn a generative model alongside an inference\nmodel. Generative autoencoders are those which are trained to softly enforce a\nprior on the latent distribution learned by the inference model. We call the\ndistribution to which the inference model maps observed samples, the learned\nlatent distribution, which may not be consistent with the prior. We formulate a\nMarkov chain Monte Carlo (MCMC) sampling process, equivalent to iteratively\ndecoding and encoding, which allows us to sample from the learned latent\ndistribution. Since, the generative model learns to map from the learned latent\ndistribution, rather than the prior, we may use MCMC to improve the quality of\nsamples drawn from the generative model, especially when the learned latent\ndistribution is far from the prior. Using MCMC sampling, we are able to reveal\npreviously unseen differences between generative autoencoders trained either\nwith or without a denoising criterion.","url_abs":"http://arxiv.org/abs/1610.09296v3","url_pdf":"http://arxiv.org/pdf/1610.09296v3.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":"improving-sampling-from-generative","repo_url":"https://github.com/Kaixhin/Autoencoders","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"torch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}