{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/on-mixup-regularization","title":"On Mixup Regularization","arxiv_id":"2006.06049","date":"2020-06-10","proceeding":null,"authors":["Luigi Carratino","Moustapha Cissé","Rodolphe Jenatton","Jean-Philippe Vert"],"abstract":"Mixup is a data augmentation technique that creates new examples as convex combinations of training points and labels. This simple technique has empirically shown to improve the accuracy of many state-of-the-art models in different settings and applications, but the reasons behind this empirical success remain poorly understood. In this paper we take a substantial step in explaining the theoretical foundations of Mixup, by clarifying its regularization effects. We show that Mixup can be interpreted as standard empirical risk minimization estimator subject to a combination of data transformation and random perturbation of the transformed data. We gain two core insights from this new interpretation. First, the data transformation suggests that, at test time, a model trained with Mixup should also be applied to transformed data, a one-line change in code that we show empirically to improve both accuracy and calibration of the prediction. Second, we show how the random perturbation of the new interpretation of Mixup induces multiple known regularization schemes, including label smoothing and reduction of the Lipschitz constant of the estimator. These schemes interact synergistically with each other, resulting in a self calibrated and effective regularization effect that prevents overfitting and overconfident predictions. We corroborate our theoretical analysis with experiments that support our conclusions.","url_abs":"https://arxiv.org/abs/2006.06049v3","url_pdf":"https://arxiv.org/pdf/2006.06049v3.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":"on-mixup-regularization","repo_url":"https://github.com/google/uncertainty-baselines/tree/master/baselines/imagenet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"mixup","method_name":"Mixup"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-objectnet","task":"Image Classification","dataset":"ObjectNet","model":"ResNet-50 + MixUp (rescaled)","rank_in_archive_order":75,"of":106,"metrics":{"Top-1 Accuracy":"28.37"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2006.06049","atlas_url":"https://app.syntology.ai/?focus=2006.06049","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2006.06049"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2006.06049\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2006.06049"},"call":"get_concepts_for_paper(arxiv_id=\"2006.06049\")"}],"by_repo":[{"repo":"google/uncertainty-baselines","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["2006.10108","2006.13570"],"harvested_for_calls":[{"arxiv_id":"2006.10108","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2006.10108"},"call":"get_harvested_code_for_paper(arxiv_id=\"2006.10108\")"},{"arxiv_id":"2006.13570","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2006.13570"},"call":"get_harvested_code_for_paper(arxiv_id=\"2006.13570\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"37086fed5d56809cc050dd47bd6b63fb93feded80a59984d9b94770adbd33095","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}