{"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/unsupervised-generative-modeling-using-matrix","title":"Unsupervised Generative Modeling Using Matrix Product States","arxiv_id":"1709.01662","date":"2017-09-06","proceeding":null,"authors":["Zhao-Yu Han","Jun Wang","Heng Fan","Lei Wang","Pan Zhang"],"abstract":"Generative modeling, which learns joint probability distribution from data\nand generates samples according to it, is an important task in machine learning\nand artificial intelligence. Inspired by probabilistic interpretation of\nquantum physics, we propose a generative model using matrix product states,\nwhich is a tensor network originally proposed for describing (particularly\none-dimensional) entangled quantum states. Our model enjoys efficient learning\nanalogous to the density matrix renormalization group method, which allows\ndynamically adjusting dimensions of the tensors and offers an efficient direct\nsampling approach for generative tasks. We apply our method to generative\nmodeling of several standard datasets including the Bars and Stripes, random\nbinary patterns and the MNIST handwritten digits to illustrate the abilities,\nfeatures and drawbacks of our model over popular generative models such as\nHopfield model, Boltzmann machines and generative adversarial networks. Our\nwork sheds light on many interesting directions of future exploration on the\ndevelopment of quantum-inspired algorithms for unsupervised machine learning,\nwhich are promisingly possible to be realized on quantum devices.","url_abs":"http://arxiv.org/abs/1709.01662v3","url_pdf":"http://arxiv.org/pdf/1709.01662v3.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":"unsupervised-generative-modeling-using-matrix","repo_url":"https://github.com/congzlwag/UnsupGenModbyMPS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.01662","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}