{"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/uncertainty-estimation-via-stochastic-batch","title":"Uncertainty Estimation via Stochastic Batch Normalization","arxiv_id":"1802.04893","date":"2018-02-13","proceeding":null,"authors":["Andrei Atanov","Arsenii Ashukha","Dmitry Molchanov","Kirill Neklyudov","Dmitry Vetrov"],"abstract":"In this work, we investigate Batch Normalization technique and propose its\nprobabilistic interpretation. We propose a probabilistic model and show that\nBatch Normalization maximazes the lower bound of its marginalized\nlog-likelihood. Then, according to the new probabilistic model, we design an\nalgorithm which acts consistently during train and test. However, inference\nbecomes computationally inefficient. To reduce memory and computational cost,\nwe propose Stochastic Batch Normalization -- an efficient approximation of\nproper inference procedure. This method provides us with a scalable uncertainty\nestimation technique. We demonstrate the performance of Stochastic Batch\nNormalization on popular architectures (including deep convolutional\narchitectures: VGG-like and ResNets) for MNIST and CIFAR-10 datasets.","url_abs":"http://arxiv.org/abs/1802.04893v2","url_pdf":"http://arxiv.org/pdf/1802.04893v2.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":"uncertainty-estimation-via-stochastic-batch","repo_url":"https://github.com/Glutamat42/mcbn-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.04893","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}