{"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/unraveling-the-enigma-of-double-descent-an-in","title":"Unraveling the Enigma of Double Descent: An In-depth Analysis through the Lens of Learned Feature Space","arxiv_id":"2310.13572","date":"2023-10-20","proceeding":null,"authors":["Yufei Gu","Xiaoqing Zheng","Tomaso Aste"],"abstract":"Double descent presents a counter-intuitive aspect within the machine learning domain, and researchers have observed its manifestation in various models and tasks. While some theoretical explanations have been proposed for this phenomenon in specific contexts, an accepted theory to account for its occurrence in deep learning remains yet to be established. In this study, we revisit the phenomenon of double descent and demonstrate that its occurrence is strongly influenced by the presence of noisy data. Through conducting a comprehensive analysis of the feature space of learned representations, we unveil that double descent arises in imperfect models trained with noisy data. We argue that double descent is a consequence of the model first learning the noisy data until interpolation and then adding implicit regularization via over-parameterization acquiring therefore capability to separate the information from the noise.","url_abs":"https://arxiv.org/abs/2310.13572v3","url_pdf":"https://arxiv.org/pdf/2310.13572v3.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":"unraveling-the-enigma-of-double-descent-an-in","repo_url":"https://github.com/yufei-gu-451/double_descent_inference","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2310.13572","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.13572"}},"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/yufei-gu-451/double_descent_inference","reach":null}],"summary":{"ran_honours":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":"f0d5ff651ecb3e16","entry":"get_test_accuracy","repo":"yufei-gu-451/double_descent_inference","repo_kind":"official","path":"scripts/noisy_label_test.py","file_url":"https://github.com/yufei-gu-451/double_descent_inference/blob/HEAD/scripts/noisy_label_test.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f0d5ff651ecb3e16"}},{"code_sha256_prefix":"5358ba707d19b6cc","entry":"get_test_losses","repo":"yufei-gu-451/double_descent_inference","repo_kind":"official","path":"scripts/noisy_label_test.py","file_url":"https://github.com/yufei-gu-451/double_descent_inference/blob/HEAD/scripts/noisy_label_test.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5358ba707d19b6cc"}},{"code_sha256_prefix":"f049170963ba8a2a","entry":"get_train_losses","repo":"yufei-gu-451/double_descent_inference","repo_kind":"official","path":"scripts/noisy_label_test.py","file_url":"https://github.com/yufei-gu-451/double_descent_inference/blob/HEAD/scripts/noisy_label_test.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f049170963ba8a2a"}},{"code_sha256_prefix":"1eb6652839e9f2de","entry":"train_and_evaluate_model","repo":"yufei-gu-451/double_descent_inference","repo_kind":"official","path":"scripts/cifar_dd_exp.py","file_url":"https://github.com/yufei-gu-451/double_descent_inference/blob/HEAD/scripts/cifar_dd_exp.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1eb6652839e9f2de"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}