{"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-onset-of-variance-limited-behavior-for","title":"The Onset of Variance-Limited Behavior for Networks in the Lazy and Rich Regimes","arxiv_id":"2212.12147","date":"2022-12-23","proceeding":null,"authors":["Alexander Atanasov","Blake Bordelon","Sabarish Sainathan","Cengiz Pehlevan"],"abstract":"For small training set sizes $P$, the generalization error of wide neural networks is well-approximated by the error of an infinite width neural network (NN), either in the kernel or mean-field/feature-learning regime. However, after a critical sample size $P^*$, we empirically find the finite-width network generalization becomes worse than that of the infinite width network. In this work, we empirically study the transition from infinite-width behavior to this variance limited regime as a function of sample size $P$ and network width $N$. We find that finite-size effects can become relevant for very small dataset sizes on the order of $P^* \\sim \\sqrt{N}$ for polynomial regression with ReLU networks. We discuss the source of these effects using an argument based on the variance of the NN's final neural tangent kernel (NTK). This transition can be pushed to larger $P$ by enhancing feature learning or by ensemble averaging the networks. We find that the learning curve for regression with the final NTK is an accurate approximation of the NN learning curve. Using this, we provide a toy model which also exhibits $P^* \\sim \\sqrt{N}$ scaling and has $P$-dependent benefits from feature learning.","url_abs":"https://arxiv.org/abs/2212.12147v1","url_pdf":"https://arxiv.org/pdf/2212.12147v1.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-onset-of-variance-limited-behavior-for","repo_url":"https://github.com/Pehlevan-Group/onset-of-variance","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"ntk","method_name":"NTK"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2212.12147","atlas_url":"https://app.syntology.ai/?focus=2212.12147","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.12147"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Pehlevan-Group/onset-of-variance","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"f004446bc66cb9b1","entry":"generate_synth_data","repo":"Pehlevan-Group/onset-of-variance","repo_kind":"official","path":"Scripts/pn_sweeps.py","file_url":"https://github.com/Pehlevan-Group/onset-of-variance/blob/HEAD/Scripts/pn_sweeps.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f004446bc66cb9b1"}},{"code_sha256_prefix":"af71a7216eaf89bc","entry":"time_diff","repo":"Pehlevan-Group/onset-of-variance","repo_kind":"official","path":"Scripts/pn_sweeps.py","file_url":"https://github.com/Pehlevan-Group/onset-of-variance/blob/HEAD/Scripts/pn_sweeps.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"af71a7216eaf89bc"}},{"code_sha256_prefix":"6686eb1857e5c305","entry":"tree_unstack","repo":"Pehlevan-Group/onset-of-variance","repo_kind":"official","path":"Scripts/pn_sweeps.py","file_url":"https://github.com/Pehlevan-Group/onset-of-variance/blob/HEAD/Scripts/pn_sweeps.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6686eb1857e5c305"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}