{"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/from-monte-carlo-to-las-vegas-improving","title":"From Monte Carlo to Las Vegas: Improving Restricted Boltzmann Machine Training Through Stopping Sets","arxiv_id":"1711.08442","date":"2017-11-22","proceeding":null,"authors":["Pedro H. P. Savarese","Mayank Kakodkar","Bruno Ribeiro"],"abstract":"We propose a Las Vegas transformation of Markov Chain Monte Carlo (MCMC)\nestimators of Restricted Boltzmann Machines (RBMs). We denote our approach\nMarkov Chain Las Vegas (MCLV). MCLV gives statistical guarantees in exchange\nfor random running times. MCLV uses a stopping set built from the training data\nand has maximum number of Markov chain steps K (referred as MCLV-K). We present\na MCLV-K gradient estimator (LVS-K) for RBMs and explore the correspondence and\ndifferences between LVS-K and Contrastive Divergence (CD-K), with LVS-K\nsignificantly outperforming CD-K training RBMs over the MNIST dataset,\nindicating MCLV to be a promising direction in learning generative models.","url_abs":"http://arxiv.org/abs/1711.08442v1","url_pdf":"http://arxiv.org/pdf/1711.08442v1.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":"from-monte-carlo-to-las-vegas-improving","repo_url":"https://github.com/PurdueMINDS/MCLV-RBM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"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}