{"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/spectrum-dependent-learning-curves-in-kernel","title":"Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks","arxiv_id":"2002.02561","date":"2020-02-07","proceeding":"ICML 2020 1","authors":["Blake Bordelon","Abdulkadir Canatar","Cengiz Pehlevan"],"abstract":"We derive analytical expressions for the generalization performance of kernel regression as a function of the number of training samples using theoretical methods from Gaussian processes and statistical physics. Our expressions apply to wide neural networks due to an equivalence between training them and kernel regression with the Neural Tangent Kernel (NTK). By computing the decomposition of the total generalization error due to different spectral components of the kernel, we identify a new spectral principle: as the size of the training set grows, kernel machines and neural networks fit successively higher spectral modes of the target function. When data are sampled from a uniform distribution on a high-dimensional hypersphere, dot product kernels, including NTK, exhibit learning stages where different frequency modes of the target function are learned. We verify our theory with simulations on synthetic data and MNIST dataset.","url_abs":"https://arxiv.org/abs/2002.02561v7","url_pdf":"https://arxiv.org/pdf/2002.02561v7.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":"spectrum-dependent-learning-curves-in-kernel","repo_url":"https://github.com/Pehlevan-Group/NTK_Learning_Curves","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"gaussian-processes","task_name":"Gaussian Processes"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"ntk","method_name":"NTK"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2002.02561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.02561"}},"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/Pehlevan-Group/NTK_Learning_Curves","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":11},"by_repo_kind":{"official":{"samples":11,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"c0a1b18bbba5a6d7","entry":"Dot_Phi_kernel","repo":"Pehlevan-Group/NTK_Learning_Curves","repo_kind":"official","path":"ntk_generalization/utils/compute_NTK_spectrum.py","file_url":"https://github.com/Pehlevan-Group/NTK_Learning_Curves/blob/HEAD/ntk_generalization/utils/compute_NTK_spectrum.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c0a1b18bbba5a6d7"}},{"code_sha256_prefix":"97ec6eb318c7be10","entry":"NTK_iter","repo":"Pehlevan-Group/NTK_Learning_Curves","repo_kind":"official","path":"ntk_generalization/utils/compute_NTK_spectrum.py","file_url":"https://github.com/Pehlevan-Group/NTK_Learning_Curves/blob/HEAD/ntk_generalization/utils/compute_NTK_spectrum.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"97ec6eb318c7be10"}},{"code_sha256_prefix":"484cc43a4193ae00","entry":"Phi_kernel","repo":"Pehlevan-Group/NTK_Learning_Curves","repo_kind":"official","path":"ntk_generalization/utils/compute_NTK_spectrum.py","file_url":"https://github.com/Pehlevan-Group/NTK_Learning_Curves/blob/HEAD/ntk_generalization/utils/compute_NTK_spectrum.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"484cc43a4193ae00"}},{"code_sha256_prefix":"478d7f4476ce4d91","entry":"area_ratio","repo":"Pehlevan-Group/NTK_Learning_Curves","repo_kind":"official","path":"ntk_generalization/utils/gegenbauer.py","file_url":"https://github.com/Pehlevan-Group/NTK_Learning_Curves/blob/HEAD/ntk_generalization/utils/gegenbauer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"478d7f4476ce4d91"}},{"code_sha256_prefix":"8d9c2ce07937ea8a","entry":"f","repo":"Pehlevan-Group/NTK_Learning_Curves","repo_kind":"official","path":"ntk_generalization/utils/theory_lc.py","file_url":"https://github.com/Pehlevan-Group/NTK_Learning_Curves/blob/HEAD/ntk_generalization/utils/theory_lc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8d9c2ce07937ea8a"}},{"code_sha256_prefix":"bbdb3e541858a2b8","entry":"fp","repo":"Pehlevan-Group/NTK_Learning_Curves","repo_kind":"official","path":"ntk_generalization/utils/theory_lc.py","file_url":"https://github.com/Pehlevan-Group/NTK_Learning_Curves/blob/HEAD/ntk_generalization/utils/theory_lc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bbdb3e541858a2b8"}},{"code_sha256_prefix":"306d17476ab3ed15","entry":"gegenbauer_loop","repo":"Pehlevan-Group/NTK_Learning_Curves","repo_kind":"official","path":"ntk_generalization/utils/gegenbauer.py","file_url":"https://github.com/Pehlevan-Group/NTK_Learning_Curves/blob/HEAD/ntk_generalization/utils/gegenbauer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"306d17476ab3ed15"}},{"code_sha256_prefix":"04f0be8b1c7a3ef9","entry":"get_gegenbauer_lax","repo":"Pehlevan-Group/NTK_Learning_Curves","repo_kind":"official","path":"ntk_generalization/utils/gegenbauer.py","file_url":"https://github.com/Pehlevan-Group/NTK_Learning_Curves/blob/HEAD/ntk_generalization/utils/gegenbauer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"04f0be8b1c7a3ef9"}},{"code_sha256_prefix":"3ab0c81e1d99aed1","entry":"sample_random_points","repo":"Pehlevan-Group/NTK_Learning_Curves","repo_kind":"official","path":"ntk_generalization/kernel_regression_lc.py","file_url":"https://github.com/Pehlevan-Group/NTK_Learning_Curves/blob/HEAD/ntk_generalization/kernel_regression_lc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ab0c81e1d99aed1"}},{"code_sha256_prefix":"30f31a745d3b7656","entry":"sample_random_points_jit","repo":"Pehlevan-Group/NTK_Learning_Curves","repo_kind":"official","path":"ntk_generalization/two_layer.py","file_url":"https://github.com/Pehlevan-Group/NTK_Learning_Curves/blob/HEAD/ntk_generalization/two_layer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"30f31a745d3b7656"}},{"code_sha256_prefix":"e5b759d19e38328b","entry":"solve_implicit","repo":"Pehlevan-Group/NTK_Learning_Curves","repo_kind":"official","path":"ntk_generalization/utils/theory_lc.py","file_url":"https://github.com/Pehlevan-Group/NTK_Learning_Curves/blob/HEAD/ntk_generalization/utils/theory_lc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e5b759d19e38328b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}