{"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/training-behavior-of-deep-neural-network-in","title":"Training behavior of deep neural network in frequency domain","arxiv_id":"1807.01251","date":"2018-07-03","proceeding":null,"authors":["Zhi-Qin John Xu","Yaoyu Zhang","Yanyang Xiao"],"abstract":"Why deep neural networks (DNNs) capable of overfitting often generalize well in practice is a mystery [#zhang2016understanding]. To find a potential mechanism, we focus on the study of implicit biases underlying the training process of DNNs. In this work, for both real and synthetic datasets, we empirically find that a DNN with common settings first quickly captures the dominant low-frequency components, and then relatively slowly captures the high-frequency ones. We call this phenomenon Frequency Principle (F-Principle). The F-Principle can be observed over DNNs of various structures, activation functions, and training algorithms in our experiments. We also illustrate how the F-Principle help understand the effect of early-stopping as well as the generalization of DNNs. This F-Principle potentially provides insights into a general principle underlying DNN optimization and generalization.","url_abs":"https://arxiv.org/abs/1807.01251v6","url_pdf":"https://arxiv.org/pdf/1807.01251v6.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":"training-behavior-of-deep-neural-network-in","repo_url":"https://github.com/xuzhiqin1990/F-Principle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1807.01251","atlas_url":"https://app.syntology.ai/?focus=1807.01251","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}