{"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/re-examining-double-descent-and-scaling-laws","title":"The Shape of Generalization through the Lens of Norm-based Capacity Control","arxiv_id":"2502.01585","date":"2025-02-03","proceeding":null,"authors":["Yichen Wang","Yudong Chen","Lorenzo Rosasco","Fanghui Liu"],"abstract":"Understanding how the test risk scales with model complexity is a central question in machine learning. Classical theory is challenged by the learning curves observed for large over-parametrized deep networks. Capacity measures based on parameter count typically fail to account for these empirical observations. To tackle this challenge, we consider norm-based capacity measures and develop our study for random features based estimators, widely used as simplified theoretical models for more complex networks. In this context, we provide a precise characterization of how the estimator's norm concentrates and how it governs the associated test error. Our results show that the predicted learning curve admits a phase transition from under- to over-parameterization, but no double descent behavior. This confirms that more classical U-shaped behavior is recovered considering appropriate capacity measures based on models norms rather than size. From a technical point of view, we leverage deterministic equivalence as the key tool and further develop new deterministic quantities which are of independent interest.","url_abs":"https://arxiv.org/abs/2502.01585v2","url_pdf":"https://arxiv.org/pdf/2502.01585v2.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":"re-examining-double-descent-and-scaling-laws","repo_url":"https://github.com/yichenblue/norm-capacity","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.01585","atlas_url":"https://app.syntology.ai/?focus=2502.01585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.01585"}},"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":"deterministic:regex_extraction","url":"https://github.com/yichenblue/norm-capacity","reach":null}],"summary":{"ran_violates":1,"ran_draft_wrong":2,"ran_fixture":1},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":4,"samples":[{"code_sha256_prefix":"a4e46bd3edd53de7","entry":"compute_variance_beta","repo":"yichenblue/norm-capacity","repo_kind":"official","path":"src/Gaussian_design/random_feature_ridge_regression/random_feature_ridge_regression.py","file_url":"https://github.com/yichenblue/norm-capacity/blob/HEAD/src/Gaussian_design/random_feature_ridge_regression/random_feature_ridge_regression.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a4e46bd3edd53de7"}},{"code_sha256_prefix":"9e1fb7fda2faa973","entry":"make_resnet18k","repo":"yichenblue/norm-capacity","repo_kind":"official","path":"src/Deep_NNs/deep_double_descent_ResNet18.py","file_url":"https://github.com/yichenblue/norm-capacity/blob/HEAD/src/Deep_NNs/deep_double_descent_ResNet18.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9e1fb7fda2faa973"}},{"code_sha256_prefix":"2cd8c566c5b775b4","entry":"solve_lambda_star","repo":"yichenblue/norm-capacity","repo_kind":"official","path":"src/Gaussian_design/random_feature_ridge_regression/random_feature_ridge_regression.py","file_url":"https://github.com/yichenblue/norm-capacity/blob/HEAD/src/Gaussian_design/random_feature_ridge_regression/random_feature_ridge_regression.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2cd8c566c5b775b4"}},{"code_sha256_prefix":"290aa109a9a64251","entry":"solve_self_consistent_equations","repo":"yichenblue/norm-capacity","repo_kind":"official","path":"src/Gaussian_design/random_feature_ridge_regression/random_feature_ridge_regression.py","file_url":"https://github.com/yichenblue/norm-capacity/blob/HEAD/src/Gaussian_design/random_feature_ridge_regression/random_feature_ridge_regression.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"290aa109a9a64251"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}