{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/on-the-convergence-of-zeroth-order-federated","title":"On the Convergence of Zeroth-Order Federated Tuning for Large Language Models","arxiv_id":"2402.05926","date":"2024-02-08","proceeding":null,"authors":["Zhenqing Ling","Daoyuan Chen","Liuyi Yao","Yaliang Li","Ying Shen"],"abstract":"The confluence of Federated Learning (FL) and Large Language Models (LLMs) is ushering in a new era in privacy-preserving natural language processing. However, the intensive memory requirements for fine-tuning LLMs pose significant challenges, especially when deploying on clients with limited computational resources. To circumvent this, we explore the novel integration of Memory-efficient Zeroth-Order Optimization within a federated setting, a synergy we term as FedMeZO. Our study is the first to examine the theoretical underpinnings of FedMeZO in the context of LLMs, tackling key questions regarding the influence of large parameter spaces on optimization behavior, the establishment of convergence properties, and the identification of critical parameters for convergence to inform personalized federated strategies. Our extensive empirical evidence supports the theory, showing that FedMeZO not only converges faster than traditional first-order methods such as FedAvg but also significantly reduces GPU memory usage during training to levels comparable to those during inference. Moreover, the proposed personalized FL strategy that is built upon the theoretical insights to customize the client-wise learning rate can effectively accelerate loss reduction. We hope our work can help to bridge theoretical and practical aspects of federated fine-tuning for LLMs, thereby stimulating further advancements and research in this area.","url_abs":"https://arxiv.org/abs/2402.05926v3","url_pdf":"https://arxiv.org/pdf/2402.05926v3.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":"on-the-convergence-of-zeroth-order-federated","repo_url":"https://github.com/alibaba/federatedscope","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"privacy-preserving","task_name":"Privacy Preserving"}],"methods":[{"method_slug":"sgd","method_name":"SGD"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.05926","atlas_url":"https://app.syntology.ai/?focus=2402.05926","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2402.05926"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2402.05926\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2402.05926"},"call":"get_concepts_for_paper(arxiv_id=\"2402.05926\")"}],"by_repo":[{"repo":"alibaba/federatedscope","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["2206.03655","2305.02776"],"harvested_for_calls":[{"arxiv_id":"2206.03655","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2206.03655"},"call":"get_harvested_code_for_paper(arxiv_id=\"2206.03655\")"},{"arxiv_id":"2305.02776","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2305.02776"},"call":"get_harvested_code_for_paper(arxiv_id=\"2305.02776\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"30e9a267bb197b6683f3b5b652bb322b080d20a3fe40026eab413d5d4487fb72","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}