{"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/lora-training-in-the-ntk-regime-has-no","title":"LoRA Training in the NTK Regime has No Spurious Local Minima","arxiv_id":"2402.11867","date":"2024-02-19","proceeding":null,"authors":["Uijeong Jang","Jason D. Lee","Ernest K. Ryu"],"abstract":"Low-rank adaptation (LoRA) has become the standard approach for parameter-efficient fine-tuning of large language models (LLM), but our theoretical understanding of LoRA has been limited. In this work, we theoretically analyze LoRA fine-tuning in the neural tangent kernel (NTK) regime with $N$ data points, showing: (i) full fine-tuning (without LoRA) admits a low-rank solution of rank $r\\lesssim \\sqrt{N}$; (ii) using LoRA with rank $r\\gtrsim \\sqrt{N}$ eliminates spurious local minima, allowing gradient descent to find the low-rank solutions; (iii) the low-rank solution found using LoRA generalizes well.","url_abs":"https://arxiv.org/abs/2402.11867v3","url_pdf":"https://arxiv.org/pdf/2402.11867v3.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":"lora-training-in-the-ntk-regime-has-no","repo_url":"https://github.com/uijeongjang/lora-ntk","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.11867","atlas_url":"https://app.syntology.ai/?focus=2402.11867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11867"}},"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/uijeongjang/lora-ntk","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":2,"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":4,"samples":[{"code_sha256_prefix":"e448786d5ff1875a","entry":"default_dev_objective","repo":"uijeongjang/lora-ntk","repo_kind":"official","path":"src/trainer.py","file_url":"https://github.com/uijeongjang/lora-ntk/blob/HEAD/src/trainer.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e448786d5ff1875a"}},{"code_sha256_prefix":"126ae8eeb63d59bf","entry":"get_label","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"126ae8eeb63d59bf"}},{"code_sha256_prefix":"8e27652a29c8adcc","entry":"load_datasets","repo":"uijeongjang/lora-ntk","repo_kind":"official","path":"tools/generate_k_shot_data.py","file_url":"https://github.com/uijeongjang/lora-ntk/blob/HEAD/tools/generate_k_shot_data.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":"8e27652a29c8adcc"}},{"code_sha256_prefix":"efd1b7718b950470","entry":"split_header","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"efd1b7718b950470"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}