{"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/leveraging-the-two-timescale-regime-to","title":"Leveraging the two timescale regime to demonstrate convergence of neural networks","arxiv_id":"2304.09576","date":"2023-04-19","proceeding":null,"authors":["Pierre Marion","Raphaël Berthier"],"abstract":"We study the training dynamics of shallow neural networks, in a two-timescale regime in which the stepsizes for the inner layer are much smaller than those for the outer layer. In this regime, we prove convergence of the gradient flow to a global optimum of the non-convex optimization problem in a simple univariate setting. The number of neurons need not be asymptotically large for our result to hold, distinguishing our result from popular recent approaches such as the neural tangent kernel or mean-field regimes. Experimental illustration is provided, showing that the stochastic gradient descent behaves according to our description of the gradient flow and thus converges to a global optimum in the two-timescale regime, but can fail outside of this regime.","url_abs":"https://arxiv.org/abs/2304.09576v2","url_pdf":"https://arxiv.org/pdf/2304.09576v2.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":"leveraging-the-two-timescale-regime-to","repo_url":"https://github.com/PierreMarion23/two-timescale-nn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"two","task_name":"Vocal Bursts Valence Prediction"}],"methods":[{"method_slug":"fail","method_name":"fail"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2304.09576","atlas_url":"https://app.syntology.ai/?focus=2304.09576","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.09576"}},"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/PierreMarion23/two-timescale-nn","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"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":"1b73fec7419e97d3","entry":"fast_solution","repo":"PierreMarion23/two-timescale-nn","repo_kind":"official","path":"two_timescale_limit.py","file_url":"https://github.com/PierreMarion23/two-timescale-nn/blob/HEAD/two_timescale_limit.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":"1b73fec7419e97d3"}},{"code_sha256_prefix":"cf410b074d17a11d","entry":"sigma","repo":"PierreMarion23/two-timescale-nn","repo_kind":"official","path":"neural_network.py","file_url":"https://github.com/PierreMarion23/two-timescale-nn/blob/HEAD/neural_network.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":"cf410b074d17a11d"}},{"code_sha256_prefix":"27297c758842eb2b","entry":"slow_derivatives","repo":"PierreMarion23/two-timescale-nn","repo_kind":"official","path":"two_timescale_limit.py","file_url":"https://github.com/PierreMarion23/two-timescale-nn/blob/HEAD/two_timescale_limit.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":"27297c758842eb2b"}},{"code_sha256_prefix":"cc55c68951147641","entry":"two_timescale_limit_derivative","repo":"PierreMarion23/two-timescale-nn","repo_kind":"official","path":"two_timescale_limit.py","file_url":"https://github.com/PierreMarion23/two-timescale-nn/blob/HEAD/two_timescale_limit.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":"cc55c68951147641"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}