{"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/how-much-data-are-augmentations-worth-an","title":"How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization","arxiv_id":"2210.06441","date":"2022-10-12","proceeding":null,"authors":["Jonas Geiping","Micah Goldblum","Gowthami Somepalli","Ravid Shwartz-Ziv","Tom Goldstein","Andrew Gordon Wilson"],"abstract":"Despite the clear performance benefits of data augmentations, little is known about why they are so effective. In this paper, we disentangle several key mechanisms through which data augmentations operate. Establishing an exchange rate between augmented and additional real data, we find that in out-of-distribution testing scenarios, augmentations which yield samples that are diverse, but inconsistent with the data distribution can be even more valuable than additional training data. Moreover, we find that data augmentations which encourage invariances can be more valuable than invariance alone, especially on small and medium sized training sets. Following this observation, we show that augmentations induce additional stochasticity during training, effectively flattening the loss landscape.","url_abs":"https://arxiv.org/abs/2210.06441v2","url_pdf":"https://arxiv.org/pdf/2210.06441v2.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":"how-much-data-are-augmentations-worth-an","repo_url":"https://github.com/jonasgeiping/dataaugs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"LGPL-2.1"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.06441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06441"}},"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":"deterministic:regex_extraction","url":"https://github.com/JonasGeiping/dataaugs","reach":{"status":"ok","spdx":"LGPL-2.1"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jonasgeiping/dataaugs","reach":{"status":"ok","spdx":"LGPL-2.1"}}],"summary":{"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":3,"samples":[{"code_sha256_prefix":"7853fe975a1df816","entry":"evaluate_per_class","repo":"JonasGeiping/dataaugs","repo_kind":"official","path":"dataaug/training/training.py","file_url":"https://github.com/JonasGeiping/dataaugs/blob/HEAD/dataaug/training/training.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":"LGPL-2.1","inline_ok":false,"mcp_get_code":{"code_sha256":"7853fe975a1df816"}},{"code_sha256_prefix":"8a9718aa8b1e0a7f","entry":"get_loss_fn","repo":"JonasGeiping/dataaugs","repo_kind":"official","path":"dataaug/training/training.py","file_url":"https://github.com/JonasGeiping/dataaugs/blob/HEAD/dataaug/training/training.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":"LGPL-2.1","inline_ok":false,"mcp_get_code":{"code_sha256":"8a9718aa8b1e0a7f"}},{"code_sha256_prefix":"b31d8e52e8956a9b","entry":"train_sgd","repo":"JonasGeiping/dataaugs","repo_kind":"official","path":"dataaug/training/training.py","file_url":"https://github.com/JonasGeiping/dataaugs/blob/HEAD/dataaug/training/training.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"LGPL-2.1","inline_ok":false,"mcp_get_code":{"code_sha256":"b31d8e52e8956a9b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}