{"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/on-the-generalization-effects-of-linear","title":"On the Generalization Effects of Linear Transformations in Data Augmentation","arxiv_id":"2005.00695","date":"2020-05-02","proceeding":"ICML 2020 1","authors":["Sen Wu","Hongyang R. Zhang","Gregory Valiant","Christopher Ré"],"abstract":"Data augmentation is a powerful technique to improve performance in applications such as image and text classification tasks. Yet, there is little rigorous understanding of why and how various augmentations work. In this work, we consider a family of linear transformations and study their effects on the ridge estimator in an over-parametrized linear regression setting. First, we show that transformations that preserve the labels of the data can improve estimation by enlarging the span of the training data. Second, we show that transformations that mix data can improve estimation by playing a regularization effect. Finally, we validate our theoretical insights on MNIST. Based on the insights, we propose an augmentation scheme that searches over the space of transformations by how uncertain the model is about the transformed data. We validate our proposed scheme on image and text datasets. For example, our method outperforms random sampling methods by 1.24% on CIFAR-100 using Wide-ResNet-28-10. Furthermore, we achieve comparable accuracy to the SoTA Adversarial AutoAugment on CIFAR-10, CIFAR-100, SVHN, and ImageNet datasets.","url_abs":"https://arxiv.org/abs/2005.00695v3","url_pdf":"https://arxiv.org/pdf/2005.00695v3.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-the-generalization-effects-of-linear","repo_url":"https://github.com/SenWu/dauphin","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"on-the-generalization-effects-of-linear","repo_url":"https://github.com/adam-mehdi/MuarAugment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[{"method_slug":"autoaugment","method_name":"AutoAugment"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"linear-regression","method_name":"Linear Regression"},{"method_slug":"randaugment","method_name":"RandAugment"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2005.00695","atlas_url":"https://app.syntology.ai/?focus=2005.00695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00695"}},"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/SenWu/dauphin","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/adam-mehdi/MuarAugment","reach":null}],"summary":{"ran":3,"ran_honours":1,"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":3,"repositories":1},"listed":{"samples":4,"ran":1,"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":"be948f6069b9a943","entry":"MixUpCrossEntropy","repo":"adam-mehdi/MuarAugment","repo_kind":"listed","path":"muar/augmentations.py","file_url":"https://github.com/adam-mehdi/MuarAugment/blob/HEAD/muar/augmentations.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"be948f6069b9a943"}},{"code_sha256_prefix":"9ce5cddeac7a72b0","entry":"conv3x3","repo":"SenWu/dauphin","repo_kind":"official","path":"dauphin/image/models/pyramidnet.py","file_url":"https://github.com/SenWu/dauphin/blob/HEAD/dauphin/image/models/pyramidnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9ce5cddeac7a72b0"}},{"code_sha256_prefix":"8766441052d7093a","entry":"get_alpha_beta","repo":"SenWu/dauphin","repo_kind":"official","path":"dauphin/image/models/shake_shake_function.py","file_url":"https://github.com/SenWu/dauphin/blob/HEAD/dauphin/image/models/shake_shake_function.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8766441052d7093a"}},{"code_sha256_prefix":"a5f3e16641cea20d","entry":"parse_sequence","repo":"senwu/dauphin","repo_kind":"official","path":"dauphin/image/augment_policy.py","file_url":"https://github.com/senwu/dauphin/blob/HEAD/dauphin/image/augment_policy.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a5f3e16641cea20d"}},{"code_sha256_prefix":"2f969dec47d024ae","entry":"BatchRandAugment","repo":"adam-mehdi/MuarAugment","repo_kind":"listed","path":"muar/augmentations.py","file_url":"https://github.com/adam-mehdi/MuarAugment/blob/HEAD/muar/augmentations.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2f969dec47d024ae"}},{"code_sha256_prefix":"d823826c5d2d0f05","entry":"MuAugment","repo":"adam-mehdi/MuarAugment","repo_kind":"listed","path":"muar/augmentations.py","file_url":"https://github.com/adam-mehdi/MuarAugment/blob/HEAD/muar/augmentations.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d823826c5d2d0f05"}},{"code_sha256_prefix":"056902da11d3f6b0","entry":"conv3x3","repo":"SenWu/dauphin","repo_kind":"official","path":"dauphin/image/models/wide_resnet.py","file_url":"https://github.com/SenWu/dauphin/blob/HEAD/dauphin/image/models/wide_resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"056902da11d3f6b0"}},{"code_sha256_prefix":"a56a697ec3f193c1","entry":"kornia_list","repo":"adam-mehdi/MuarAugment","repo_kind":"listed","path":"muar/augmentations.py","file_url":"https://github.com/adam-mehdi/MuarAugment/blob/HEAD/muar/augmentations.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a56a697ec3f193c1"}},{"code_sha256_prefix":"e10d4efe152bbf23","entry":"load_json","repo":"SenWu/dauphin","repo_kind":"official","path":"dauphin/utils.py","file_url":"https://github.com/SenWu/dauphin/blob/HEAD/dauphin/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e10d4efe152bbf23"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}