{"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/the-memory-perturbation-equation","title":"The Memory Perturbation Equation: Understanding Model's Sensitivity to Data","arxiv_id":"2310.19273","date":"2023-10-30","proceeding":null,"authors":["Peter Nickl","Lu Xu","Dharmesh Tailor","Thomas Möllenhoff","Mohammad Emtiyaz Khan"],"abstract":"Understanding model's sensitivity to its training data is crucial but can also be challenging and costly, especially during training. To simplify such issues, we present the Memory-Perturbation Equation (MPE) which relates model's sensitivity to perturbation in its training data. Derived using Bayesian principles, the MPE unifies existing sensitivity measures, generalizes them to a wide-variety of models and algorithms, and unravels useful properties regarding sensitivities. Our empirical results show that sensitivity estimates obtained during training can be used to faithfully predict generalization on unseen test data. The proposed equation is expected to be useful for future research on robust and adaptive learning.","url_abs":"https://arxiv.org/abs/2310.19273v2","url_pdf":"https://arxiv.org/pdf/2310.19273v2.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":"the-memory-perturbation-equation","repo_url":"https://github.com/team-approx-bayes/memory-perturbation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"sensitivity","task_name":"Sensitivity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2310.19273","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.19273"}},"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/team-approx-bayes/memory-perturbation","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"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":"9aa2419a56b755c9","entry":"train_one_epoch_iblr","repo":"team-approx-bayes/memory-perturbation","repo_kind":"official","path":"examples/1_loo_iterations.py","file_url":"https://github.com/team-approx-bayes/memory-perturbation/blob/HEAD/examples/1_loo_iterations.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9aa2419a56b755c9"}},{"code_sha256_prefix":"4714ed814b4d5961","entry":"train_one_epoch_sgd_adam","repo":"team-approx-bayes/memory-perturbation","repo_kind":"official","path":"examples/1_loo_iterations.py","file_url":"https://github.com/team-approx-bayes/memory-perturbation/blob/HEAD/examples/1_loo_iterations.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4714ed814b4d5961"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}