{"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/generalization-despite-overfitting-in-quantum","title":"Generalization despite overfitting in quantum machine learning models","arxiv_id":"2209.05523","date":"2022-09-12","proceeding":null,"authors":["Evan Peters","Maria Schuld"],"abstract":"The widespread success of deep neural networks has revealed a surprise in classical machine learning: very complex models often generalize well while simultaneously overfitting training data. This phenomenon of benign overfitting has been studied for a variety of classical models with the goal of better understanding the mechanisms behind deep learning. Characterizing the phenomenon in the context of quantum machine learning might similarly improve our understanding of the relationship between overfitting, overparameterization, and generalization. In this work, we provide a characterization of benign overfitting in quantum models. To do this, we derive the behavior of a classical interpolating Fourier features models for regression on noisy signals, and show how a class of quantum models exhibits analogous features, thereby linking the structure of quantum circuits (such as data-encoding and state preparation operations) to overparameterization and overfitting in quantum models. We intuitively explain these features according to the ability of the quantum model to interpolate noisy data with locally \"spiky\" behavior and provide a concrete demonstration example of benign overfitting.","url_abs":"https://arxiv.org/abs/2209.05523v2","url_pdf":"https://arxiv.org/pdf/2209.05523v2.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"generalization-despite-overfitting-in-quantum","repo_url":"https://github.com/peterse/benign-overfitting-quantum","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2209.05523","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.05523"}},"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/peterse/benign-overfitting-quantum","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":"2f8142f97e9cf902","entry":"dft","repo":"peterse/benign-overfitting-quantum","repo_kind":"official","path":"qml-bo/qmlbo/signals.py","file_url":"https://github.com/peterse/benign-overfitting-quantum/blob/HEAD/qml-bo/qmlbo/signals.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":"2f8142f97e9cf902"}},{"code_sha256_prefix":"c383ad897264676b","entry":"get_fourier_coeffs","repo":"peterse/benign-overfitting-quantum","repo_kind":"official","path":"qml-bo/qmlbo/spectrum.py","file_url":"https://github.com/peterse/benign-overfitting-quantum/blob/HEAD/qml-bo/qmlbo/spectrum.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":"c383ad897264676b"}},{"code_sha256_prefix":"0df3cbfe1a2a43e1","entry":"get_frequency_spectrum","repo":"peterse/benign-overfitting-quantum","repo_kind":"official","path":"qml-bo/qmlbo/spectrum.py","file_url":"https://github.com/peterse/benign-overfitting-quantum/blob/HEAD/qml-bo/qmlbo/spectrum.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":"0df3cbfe1a2a43e1"}},{"code_sha256_prefix":"a6b60e6ffaa94590","entry":"get_model_nu_opt","repo":"peterse/benign-overfitting-quantum","repo_kind":"official","path":"qml-bo/qmlbo/spectrum.py","file_url":"https://github.com/peterse/benign-overfitting-quantum/blob/HEAD/qml-bo/qmlbo/spectrum.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":"a6b60e6ffaa94590"}},{"code_sha256_prefix":"2bbe937f867f5d81","entry":"get_odd_fourier_coefficients","repo":"peterse/benign-overfitting-quantum","repo_kind":"official","path":"qml-bo/qmlbo/signals.py","file_url":"https://github.com/peterse/benign-overfitting-quantum/blob/HEAD/qml-bo/qmlbo/signals.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":"2bbe937f867f5d81"}},{"code_sha256_prefix":"13d348689a025a78","entry":"ncr","repo":"peterse/benign-overfitting-quantum","repo_kind":"official","path":"qml-bo/qmlbo/bitops.py","file_url":"https://github.com/peterse/benign-overfitting-quantum/blob/HEAD/qml-bo/qmlbo/bitops.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":"13d348689a025a78"}},{"code_sha256_prefix":"efde7547262b4011","entry":"safecast_log2","repo":"peterse/benign-overfitting-quantum","repo_kind":"official","path":"qml-bo/qmlbo/models.py","file_url":"https://github.com/peterse/benign-overfitting-quantum/blob/HEAD/qml-bo/qmlbo/models.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":"efde7547262b4011"}},{"code_sha256_prefix":"e483fac3704076e8","entry":"shift_ternary","repo":"peterse/benign-overfitting-quantum","repo_kind":"official","path":"qml-bo/qmlbo/bitops.py","file_url":"https://github.com/peterse/benign-overfitting-quantum/blob/HEAD/qml-bo/qmlbo/bitops.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":"e483fac3704076e8"}},{"code_sha256_prefix":"b369bf6d7f94ffb3","entry":"symmetric_cohort_generator","repo":"peterse/benign-overfitting-quantum","repo_kind":"official","path":"qml-bo/qmlbo/signals.py","file_url":"https://github.com/peterse/benign-overfitting-quantum/blob/HEAD/qml-bo/qmlbo/signals.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":"b369bf6d7f94ffb3"}},{"code_sha256_prefix":"5c558c93a5aaf837","entry":"ternary","repo":"peterse/benign-overfitting-quantum","repo_kind":"official","path":"qml-bo/qmlbo/bitops.py","file_url":"https://github.com/peterse/benign-overfitting-quantum/blob/HEAD/qml-bo/qmlbo/bitops.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":"5c558c93a5aaf837"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}