{"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/learning-towards-minimum-hyperspherical","title":"Learning towards Minimum Hyperspherical Energy","arxiv_id":"1805.09298","date":"2018-05-23","proceeding":"NeurIPS 2018 12","authors":["Weiyang Liu","Rongmei Lin","Zhen Liu","Lixin Liu","Zhiding Yu","Bo Dai","Le Song"],"abstract":"Neural networks are a powerful class of nonlinear functions that can be trained end-to-end on various applications. While the over-parametrization nature in many neural networks renders the ability to fit complex functions and the strong representation power to handle challenging tasks, it also leads to highly correlated neurons that can hurt the generalization ability and incur unnecessary computation cost. As a result, how to regularize the network to avoid undesired representation redundancy becomes an important issue. To this end, we draw inspiration from a well-known problem in physics -- Thomson problem, where one seeks to find a state that distributes N electrons on a unit sphere as evenly as possible with minimum potential energy. In light of this intuition, we reduce the redundancy regularization problem to generic energy minimization, and propose a minimum hyperspherical energy (MHE) objective as generic regularization for neural networks. We also propose a few novel variants of MHE, and provide some insights from a theoretical point of view. Finally, we apply neural networks with MHE regularization to several challenging tasks. Extensive experiments demonstrate the effectiveness of our intuition, by showing the superior performance with MHE regularization.","url_abs":"https://arxiv.org/abs/1805.09298v9","url_pdf":"https://arxiv.org/pdf/1805.09298v9.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":"learning-towards-minimum-hyperspherical","repo_url":"https://github.com/dtch1997/mhe-tf2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"learning-towards-minimum-hyperspherical","repo_url":"https://github.com/jperezlapillo/Hyper-Wave-U-Net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-towards-minimum-hyperspherical","repo_url":"https://github.com/wy1iu/MHE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-towards-minimum-hyperspherical","repo_url":"https://github.com/wy1iu/sphereface-plus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.09298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.09298"}},"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/wy1iu/MHE","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dtch1997/mhe-tf2","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jperezlapillo/Hyper-Wave-U-Net","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wy1iu/sphereface-plus","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"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":"6f66e23b80867737","entry":"get_is","repo":"wy1iu/MHE","repo_kind":"listed","path":"MHE-GAN/non-sn-model/tf_inception.py","file_url":"https://github.com/wy1iu/MHE/blob/HEAD/MHE-GAN/non-sn-model/tf_inception.py","link_basis":"harvester_set","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":"6f66e23b80867737"}},{"code_sha256_prefix":"6e59af1261b4f2d3","entry":"scope_has_variables","repo":"wy1iu/MHE","repo_kind":"listed","path":"MHE-GAN/non-sn-model/libs/ops.py","file_url":"https://github.com/wy1iu/MHE/blob/HEAD/MHE-GAN/non-sn-model/libs/ops.py","link_basis":"harvester_set","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":"6e59af1261b4f2d3"}},{"code_sha256_prefix":"ba2f41a94dd7e578","entry":"spectral_normed_weight","repo":"wy1iu/MHE","repo_kind":"listed","path":"MHE-GAN/non-sn-model/libs/sn.py","file_url":"https://github.com/wy1iu/MHE/blob/HEAD/MHE-GAN/non-sn-model/libs/sn.py","link_basis":"harvester_set","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":"ba2f41a94dd7e578"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}