{"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/parsimonious-bayesian-deep-networks","title":"Parsimonious Bayesian deep networks","arxiv_id":"1805.08719","date":"2018-05-22","proceeding":"NeurIPS 2018 12","authors":["Mingyuan Zhou"],"abstract":"Combining Bayesian nonparametrics and a forward model selection strategy, we\nconstruct parsimonious Bayesian deep networks (PBDNs) that infer\ncapacity-regularized network architectures from the data and require neither\ncross-validation nor fine-tuning when training the model. One of the two\nessential components of a PBDN is the development of a special infinite-wide\nsingle-hidden-layer neural network, whose number of active hidden units can be\ninferred from the data. The other one is the construction of a greedy\nlayer-wise learning algorithm that uses a forward model selection criterion to\ndetermine when to stop adding another hidden layer. We develop both Gibbs\nsampling and stochastic gradient descent based maximum a posteriori inference\nfor PBDNs, providing state-of-the-art classification accuracy and interpretable\ndata subtypes near the decision boundaries, while maintaining low computational\ncomplexity for out-of-sample prediction.","url_abs":"http://arxiv.org/abs/1805.08719v3","url_pdf":"http://arxiv.org/pdf/1805.08719v3.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":"parsimonious-bayesian-deep-networks","repo_url":"https://github.com/mingyuanzhou/PBDN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"parsimonious-bayesian-deep-networks","repo_url":"https://github.com/ethanhezhao/WEDTM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"model-selection","task_name":"Model Selection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.08719","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}