{"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/butterfly-net-optimal-function-representation","title":"Butterfly-Net: Optimal Function Representation Based on Convolutional Neural Networks","arxiv_id":"1805.07451","date":"2018-05-18","proceeding":null,"authors":["Yingzhou Li","Xiuyuan Cheng","Jianfeng Lu"],"abstract":"Deep networks, especially convolutional neural networks (CNNs), have been successfully applied in various areas of machine learning as well as to challenging problems in other scientific and engineering fields. This paper introduces Butterfly-Net, a low-complexity CNN with structured and sparse cross-channel connections, together with a Butterfly initialization strategy for a family of networks. Theoretical analysis of the approximation power of Butterfly-Net to the Fourier representation of input data shows that the error decays exponentially as the depth increases. Combining Butterfly-Net with a fully connected neural network, a large class of problems are proved to be well approximated with network complexity depending on the effective frequency bandwidth instead of the input dimension. Regular CNN is covered as a special case in our analysis. Numerical experiments validate the analytical results on the approximation of Fourier kernels and energy functionals of Poisson's equations. Moreover, all experiments support that training from Butterfly initialization outperforms training from random initialization. Also, adding the remaining cross-channel connections, although significantly increase the parameter number, does not much improve the post-training accuracy and is more sensitive to data distribution.","url_abs":"https://arxiv.org/abs/1805.07451v4","url_pdf":"https://arxiv.org/pdf/1805.07451v4.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":"butterfly-net-optimal-function-representation","repo_url":"https://github.com/YingzhouLi/ButterflyNet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1805.07451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.07451"}},"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/YingzhouLi/ButterflyNet","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"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":"e1460cb8b2c0c2a4","entry":"LagrangeMat","repo":"YingzhouLi/ButterflyNet","repo_kind":"official","path":"butterflynet/utils.py","file_url":"https://github.com/YingzhouLi/ButterflyNet/blob/HEAD/butterflynet/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"e1460cb8b2c0c2a4"}},{"code_sha256_prefix":"e8beaae241a2982b","entry":"gaussianfun","repo":"YingzhouLi/ButterflyNet","repo_kind":"official","path":"butterflynet/utils.py","file_url":"https://github.com/YingzhouLi/ButterflyNet/blob/HEAD/butterflynet/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"e8beaae241a2982b"}},{"code_sha256_prefix":"068ea60e3f6f4d3e","entry":"matassign_c2c","repo":"YingzhouLi/ButterflyNet","repo_kind":"official","path":"butterflynet/utils.py","file_url":"https://github.com/YingzhouLi/ButterflyNet/blob/HEAD/butterflynet/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"068ea60e3f6f4d3e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}