{"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/are-wider-nets-better-given-the-same-number-1","title":"Are wider nets better given the same number of parameters?","arxiv_id":"2010.14495","date":"2020-10-27","proceeding":"ICLR 2021 1","authors":["Anna Golubeva","Behnam Neyshabur","Guy Gur-Ari"],"abstract":"Empirical studies demonstrate that the performance of neural networks improves with increasing number of parameters. In most of these studies, the number of parameters is increased by increasing the network width. This begs the question: Is the observed improvement due to the larger number of parameters, or is it due to the larger width itself? We compare different ways of increasing model width while keeping the number of parameters constant. We show that for models initialized with a random, static sparsity pattern in the weight tensors, network width is the determining factor for good performance, while the number of weights is secondary, as long as trainability is ensured. As a step towards understanding this effect, we analyze these models in the framework of Gaussian Process kernels. We find that the distance between the sparse finite-width model kernel and the infinite-width kernel at initialization is indicative of model performance.","url_abs":"https://arxiv.org/abs/2010.14495v2","url_pdf":"https://arxiv.org/pdf/2010.14495v2.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":"are-wider-nets-better-given-the-same-number-1","repo_url":"https://github.com/google-research/wide-sparse-nets","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"are-wider-nets-better-given-the-same-number-1","repo_url":"https://github.com/google-research/OOD-failures","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[{"method_slug":"gaussian-process","method_name":"Gaussian Process"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2010.14495","atlas_url":"https://app.syntology.ai/?focus=2010.14495","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.14495"}},"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/google-research/wide-sparse-nets","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research/OOD-failures","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"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":"d6951fc088ce5f9f","entry":"get_NWTF","repo":"google-research/wide-sparse-nets","repo_kind":"official","path":"MLP/utils.py","file_url":"https://github.com/google-research/wide-sparse-nets/blob/HEAD/MLP/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d6951fc088ce5f9f"}},{"code_sha256_prefix":"4de6225c22144c93","entry":"get_aug","repo":"google-research/wide-sparse-nets","repo_kind":"official","path":"ResNet18/get_data.py","file_url":"https://github.com/google-research/wide-sparse-nets/blob/HEAD/ResNet18/get_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4de6225c22144c93"}},{"code_sha256_prefix":"b27040a777264735","entry":"get_dataset","repo":"google-research/wide-sparse-nets","repo_kind":"official","path":"ResNet18/get_data.py","file_url":"https://github.com/google-research/wide-sparse-nets/blob/HEAD/ResNet18/get_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b27040a777264735"}},{"code_sha256_prefix":"fbba7d5fe1b01b75","entry":"get_optimizer","repo":"google-research/wide-sparse-nets","repo_kind":"official","path":"ResNet18/utils.py","file_url":"https://github.com/google-research/wide-sparse-nets/blob/HEAD/ResNet18/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fbba7d5fe1b01b75"}},{"code_sha256_prefix":"fff82f4a2d75732c","entry":"get_scheduler","repo":"google-research/wide-sparse-nets","repo_kind":"official","path":"ResNet18/utils.py","file_url":"https://github.com/google-research/wide-sparse-nets/blob/HEAD/ResNet18/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fff82f4a2d75732c"}},{"code_sha256_prefix":"3e19ee5876fe48c6","entry":"get_transform","repo":"google-research/wide-sparse-nets","repo_kind":"official","path":"ResNet18/get_data.py","file_url":"https://github.com/google-research/wide-sparse-nets/blob/HEAD/ResNet18/get_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3e19ee5876fe48c6"}},{"code_sha256_prefix":"34a6405a38352b0e","entry":"load_dataset","repo":"google-research/wide-sparse-nets","repo_kind":"official","path":"MLP/utils.py","file_url":"https://github.com/google-research/wide-sparse-nets/blob/HEAD/MLP/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"34a6405a38352b0e"}},{"code_sha256_prefix":"3b7750f512ae1d9f","entry":"pixelwise_normalization","repo":"google-research/wide-sparse-nets","repo_kind":"official","path":"MLP/utils.py","file_url":"https://github.com/google-research/wide-sparse-nets/blob/HEAD/MLP/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3b7750f512ae1d9f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}