{"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/on-the-exact-computation-of-linear-frequency","title":"On the exact computation of linear frequency principle dynamics and its generalization","arxiv_id":"2010.08153","date":"2020-10-15","proceeding":null,"authors":["Tao Luo","Zheng Ma","Zhi-Qin John Xu","Yaoyu Zhang"],"abstract":"Recent works show an intriguing phenomenon of Frequency Principle (F-Principle) that deep neural networks (DNNs) fit the target function from low to high frequency during the training, which provides insight into the training and generalization behavior of DNNs in complex tasks. In this paper, through analysis of an infinite-width two-layer NN in the neural tangent kernel (NTK) regime, we derive the exact differential equation, namely Linear Frequency-Principle (LFP) model, governing the evolution of NN output function in the frequency domain during the training. Our exact computation applies for general activation functions with no assumption on size and distribution of training data. This LFP model unravels that higher frequencies evolve polynomially or exponentially slower than lower frequencies depending on the smoothness/regularity of the activation function. We further bridge the gap between training dynamics and generalization by proving that LFP model implicitly minimizes a Frequency-Principle norm (FP-norm) of the learned function, by which higher frequencies are more severely penalized depending on the inverse of their evolution rate. Finally, we derive an \\textit{a priori} generalization error bound controlled by the FP-norm of the target function, which provides a theoretical justification for the empirical results that DNNs often generalize well for low frequency functions.","url_abs":"https://arxiv.org/abs/2010.08153v1","url_pdf":"https://arxiv.org/pdf/2010.08153v1.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":"on-the-exact-computation-of-linear-frequency","repo_url":"https://github.com/xuzhiqin1990/LFP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2010.08153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.08153"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/LFP","reach":null}],"summary":{"ran_draft_wrong":3,"ran_fixture":2,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"repositories":1}},"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":6,"samples":[{"code_sha256_prefix":"1f9dc6a32e17794f","entry":"Fbase","repo":"xuzhiqin1990/LFP","repo_kind":"official","path":"curvefitting_FI.py","file_url":"https://github.com/xuzhiqin1990/LFP/blob/HEAD/curvefitting_FI.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1f9dc6a32e17794f"}},{"code_sha256_prefix":"4923ada7d336633e","entry":"Fbase_1d","repo":"xuzhiqin1990/LFP","repo_kind":"official","path":"curvefitting_FI.py","file_url":"https://github.com/xuzhiqin1990/LFP/blob/HEAD/curvefitting_FI.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4923ada7d336633e"}},{"code_sha256_prefix":"b1a59067c8d3e9ae","entry":"Fbase_2d","repo":"xuzhiqin1990/LFP","repo_kind":"official","path":"curvefitting_FI.py","file_url":"https://github.com/xuzhiqin1990/LFP/blob/HEAD/curvefitting_FI.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b1a59067c8d3e9ae"}},{"code_sha256_prefix":"d04898a3d2cb80f4","entry":"smooth_curve","repo":"xuzhiqin1990/LFP","repo_kind":"official","path":"BasicFunc.py","file_url":"https://github.com/xuzhiqin1990/LFP/blob/HEAD/BasicFunc.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d04898a3d2cb80f4"}},{"code_sha256_prefix":"dd87064db326e501","entry":"to_one_hot","repo":"xuzhiqin1990/LFP","repo_kind":"official","path":"BasicFunc.py","file_url":"https://github.com/xuzhiqin1990/LFP/blob/HEAD/BasicFunc.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dd87064db326e501"}},{"code_sha256_prefix":"18fb061a44d0f585","entry":"plot_w","repo":"xuzhiqin1990/LFP","repo_kind":"official","path":"BasicFunc.py","file_url":"https://github.com/xuzhiqin1990/LFP/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":"18fb061a44d0f585"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}