{"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/frequency-principle-fourier-analysis-sheds","title":"Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks","arxiv_id":"1901.06523","date":"2019-01-19","proceeding":null,"authors":["Zhi-Qin John Xu","Yaoyu Zhang","Tao Luo","Yanyang Xiao","Zheng Ma"],"abstract":"We study the training process of Deep Neural Networks (DNNs) from the Fourier analysis perspective. We demonstrate a very universal Frequency Principle (F-Principle) -- DNNs often fit target functions from low to high frequencies -- on high-dimensional benchmark datasets such as MNIST/CIFAR10 and deep neural networks such as VGG16. This F-Principle of DNNs is opposite to the behavior of most conventional iterative numerical schemes (e.g., Jacobi method), which exhibit faster convergence for higher frequencies for various scientific computing problems. With a simple theory, we illustrate that this F-Principle results from the regularity of the commonly used activation functions. The F-Principle implies an implicit bias that DNNs tend to fit training data by a low-frequency function. This understanding provides an explanation of good generalization of DNNs on most real datasets and bad generalization of DNNs on parity function or randomized dataset.","url_abs":"https://arxiv.org/abs/1901.06523v7","url_pdf":"https://arxiv.org/pdf/1901.06523v7.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":"frequency-principle-fourier-analysis-sheds","repo_url":"https://github.com/lizhemin15/self-distillation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"frequency-principle-fourier-analysis-sheds","repo_url":"https://github.com/xuzhiqin1990/F-Principle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"frequency-principle-fourier-analysis-sheds","repo_url":"https://github.com/xuzhiqin1990/mscalednn","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/1901.06523","atlas_url":"https://app.syntology.ai/?focus=1901.06523","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.06523"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xuzhiqin1990/mscalednn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lizhemin15/self-distillation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xuzhiqin1990/F-Principle","reach":null}],"summary":{"ran_violates":2,"ran_honours":5,"unverified":1},"by_repo_kind":{"listed":{"samples":8,"ran":7,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":8,"samples":[{"code_sha256_prefix":"c567a9e22918a4b2","entry":"func0","repo":"xuzhiqin1990/F-Principle","repo_kind":"listed","path":"main_1d_20190924.py","file_url":"https://github.com/xuzhiqin1990/F-Principle/blob/HEAD/main_1d_20190924.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c567a9e22918a4b2"}},{"code_sha256_prefix":"eaec3a6ad43de50b","entry":"getWeightNorm","repo":"xuzhiqin1990/F-Principle","repo_kind":"listed","path":"BasicFunc.py","file_url":"https://github.com/xuzhiqin1990/F-Principle/blob/HEAD/BasicFunc.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eaec3a6ad43de50b"}},{"code_sha256_prefix":"47f4b6968afd11b4","entry":"getWeightNormLayer","repo":"xuzhiqin1990/F-Principle","repo_kind":"listed","path":"BasicFunc.py","file_url":"https://github.com/xuzhiqin1990/F-Principle/blob/HEAD/BasicFunc.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"47f4b6968afd11b4"}},{"code_sha256_prefix":"829510e90192ce5e","entry":"rand_bd","repo":"xuzhiqin1990/mscalednn","repo_kind":"listed","path":"exp/sin_M/62178/code.py","file_url":"https://github.com/xuzhiqin1990/mscalednn/blob/HEAD/exp/sin_M/62178/code.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"829510e90192ce5e"}},{"code_sha256_prefix":"06d6c667e46ee123","entry":"rand_it","repo":"xuzhiqin1990/mscalednn","repo_kind":"listed","path":"exp/sin_M/62178/code.py","file_url":"https://github.com/xuzhiqin1990/mscalednn/blob/HEAD/exp/sin_M/62178/code.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"06d6c667e46ee123"}},{"code_sha256_prefix":"2d3e248be1323d2c","entry":"sigmoid","repo":"xuzhiqin1990/F-Principle","repo_kind":"listed","path":"main_1d_20190924.py","file_url":"https://github.com/xuzhiqin1990/F-Principle/blob/HEAD/main_1d_20190924.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2d3e248be1323d2c"}},{"code_sha256_prefix":"71f9d808a0cde4de","entry":"u","repo":"xuzhiqin1990/mscalednn","repo_kind":"listed","path":"exp/sin_M/62178/code.py","file_url":"https://github.com/xuzhiqin1990/mscalednn/blob/HEAD/exp/sin_M/62178/code.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"71f9d808a0cde4de"}},{"code_sha256_prefix":"cc48b19eaf790f9e","entry":"plot_w","repo":"xuzhiqin1990/F-Principle","repo_kind":"listed","path":"BasicFunc.py","file_url":"https://github.com/xuzhiqin1990/F-Principle/blob/HEAD/BasicFunc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cc48b19eaf790f9e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}