{"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/variational-low-rank-adaptation-using-ivon","title":"Variational Low-Rank Adaptation Using IVON","arxiv_id":"2411.04421","date":"2024-11-07","proceeding":null,"authors":["Bai Cong","Nico Daheim","Yuesong Shen","Daniel Cremers","Rio Yokota","Mohammad Emtiyaz Khan","Thomas Möllenhoff"],"abstract":"We show that variational learning can significantly improve the accuracy and calibration of Low-Rank Adaptation (LoRA) without a substantial increase in the cost. We replace AdamW by the Improved Variational Online Newton (IVON) algorithm to finetune large language models. For Llama-2 with 7 billion parameters, IVON improves the accuracy over AdamW by 2.8% and expected calibration error by 4.6%. The accuracy is also better than the other Bayesian alternatives, yet the cost is lower and the implementation is easier. Our work provides additional evidence for the effectiveness of IVON for large language models. The code is available at https://github.com/team-approx-bayes/ivon-lora.","url_abs":"https://arxiv.org/abs/2411.04421v2","url_pdf":"https://arxiv.org/pdf/2411.04421v2.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":"variational-low-rank-adaptation-using-ivon","repo_url":"https://github.com/team-approx-bayes/ivon-lora","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"adamw","method_name":"AdamW"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2411.04421","atlas_url":"https://app.syntology.ai/?focus=2411.04421","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04421"}},"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/team-approx-bayes/ivon-lora","reach":{"status":"ok"}}],"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":4,"samples":[{"code_sha256_prefix":"436f4c309d8668cf","entry":"calculate_metrics","repo":"team-approx-bayes/ivon-lora","repo_kind":"official","path":"utils.py","file_url":"https://github.com/team-approx-bayes/ivon-lora/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"436f4c309d8668cf"}},{"code_sha256_prefix":"409ef49365463547","entry":"get_model_with_lora","repo":"team-approx-bayes/ivon-lora","repo_kind":"official","path":"model.py","file_url":"https://github.com/team-approx-bayes/ivon-lora/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"409ef49365463547"}},{"code_sha256_prefix":"ebd2a7cc208c71af","entry":"get_processed_datasets","repo":"team-approx-bayes/ivon-lora","repo_kind":"official","path":"data.py","file_url":"https://github.com/team-approx-bayes/ivon-lora/blob/HEAD/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ebd2a7cc208c71af"}},{"code_sha256_prefix":"d8835e01bd280f77","entry":"get_raw_datasets","repo":"team-approx-bayes/ivon-lora","repo_kind":"official","path":"data.py","file_url":"https://github.com/team-approx-bayes/ivon-lora/blob/HEAD/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d8835e01bd280f77"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}