{"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/deep-linear-networks-can-benignly-overfit","title":"Deep Linear Networks can Benignly Overfit when Shallow Ones Do","arxiv_id":"2209.09315","date":"2022-09-19","proceeding":null,"authors":["Niladri S. Chatterji","Philip M. Long"],"abstract":"We bound the excess risk of interpolating deep linear networks trained using gradient flow. In a setting previously used to establish risk bounds for the minimum $\\ell_2$-norm interpolant, we show that randomly initialized deep linear networks can closely approximate or even match known bounds for the minimum $\\ell_2$-norm interpolant. Our analysis also reveals that interpolating deep linear models have exactly the same conditional variance as the minimum $\\ell_2$-norm solution. Since the noise affects the excess risk only through the conditional variance, this implies that depth does not improve the algorithm's ability to \"hide the noise\". Our simulations verify that aspects of our bounds reflect typical behavior for simple data distributions. We also find that similar phenomena are seen in simulations with ReLU networks, although the situation there is more nuanced.","url_abs":"https://arxiv.org/abs/2209.09315v2","url_pdf":"https://arxiv.org/pdf/2209.09315v2.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":"deep-linear-networks-can-benignly-overfit","repo_url":"https://github.com/niladri-chatterji/benign-deep-linear","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2209.09315","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.09315"}},"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/niladri-chatterji/benign-deep-linear","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":10},"by_repo_kind":{"official":{"samples":10,"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":"0e4bf5add4b1b049","entry":"GaussianIID","repo":"niladri-chatterji/benign-deep-linear","repo_kind":"official","path":"src/data.py","file_url":"https://github.com/niladri-chatterji/benign-deep-linear/blob/HEAD/src/data.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":"0e4bf5add4b1b049"}},{"code_sha256_prefix":"6516763f3d5f80f5","entry":"PlantedTwoLayerIID","repo":"niladri-chatterji/benign-deep-linear","repo_kind":"official","path":"src/data.py","file_url":"https://github.com/niladri-chatterji/benign-deep-linear/blob/HEAD/src/data.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":"6516763f3d5f80f5"}},{"code_sha256_prefix":"e00b7724c0a7af44","entry":"TrainNet","repo":"niladri-chatterji/benign-deep-linear","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/niladri-chatterji/benign-deep-linear/blob/HEAD/src/utils.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":"e00b7724c0a7af44"}},{"code_sha256_prefix":"421fd51a9c0b26f0","entry":"exp1","repo":"niladri-chatterji/benign-deep-linear","repo_kind":"official","path":"src/experiments/exp1.py","file_url":"https://github.com/niladri-chatterji/benign-deep-linear/blob/HEAD/src/experiments/exp1.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":"421fd51a9c0b26f0"}},{"code_sha256_prefix":"4152f3791094346c","entry":"exp2","repo":"niladri-chatterji/benign-deep-linear","repo_kind":"official","path":"src/experiments/exp2.py","file_url":"https://github.com/niladri-chatterji/benign-deep-linear/blob/HEAD/src/experiments/exp2.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":"4152f3791094346c"}},{"code_sha256_prefix":"b61f35aca49e0b22","entry":"exp3","repo":"niladri-chatterji/benign-deep-linear","repo_kind":"official","path":"src/experiments/exp3.py","file_url":"https://github.com/niladri-chatterji/benign-deep-linear/blob/HEAD/src/experiments/exp3.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":"b61f35aca49e0b22"}},{"code_sha256_prefix":"fc5fc53e4ba3e925","entry":"exp4","repo":"niladri-chatterji/benign-deep-linear","repo_kind":"official","path":"src/experiments/exp4.py","file_url":"https://github.com/niladri-chatterji/benign-deep-linear/blob/HEAD/src/experiments/exp4.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":"fc5fc53e4ba3e925"}},{"code_sha256_prefix":"e7fda969e637db5b","entry":"exp5","repo":"niladri-chatterji/benign-deep-linear","repo_kind":"official","path":"src/experiments/exp5.py","file_url":"https://github.com/niladri-chatterji/benign-deep-linear/blob/HEAD/src/experiments/exp5.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":"e7fda969e637db5b"}},{"code_sha256_prefix":"3c1e7b0156d6a652","entry":"loss","repo":"niladri-chatterji/benign-deep-linear","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/niladri-chatterji/benign-deep-linear/blob/HEAD/src/utils.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":"3c1e7b0156d6a652"}},{"code_sha256_prefix":"a6ba49d2afc624cf","entry":"loss_net","repo":"niladri-chatterji/benign-deep-linear","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/niladri-chatterji/benign-deep-linear/blob/HEAD/src/utils.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":"a6ba49d2afc624cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}