{"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/local-flow-matching-generative-models","title":"Local Flow Matching Generative Models","arxiv_id":"2410.02548","date":"2024-10-03","proceeding":null,"authors":["Chen Xu","Xiuyuan Cheng","Yao Xie"],"abstract":"Density estimation is a fundamental problem in statistics and machine learning. We consider a modern approach using flow-based generative models, and propose Local Flow Matching ($\\texttt{LFM}$), a computational framework for density estimation based on such models, which learn a continuous and invertible flow to map noise samples to data samples. Unlike existing methods, $\\texttt{LFM}$ employs a simulation-free scheme and incrementally learns a sequence of Flow Matching sub-models. Each sub-model matches a diffusion process over a small step size in the data-to-noise direction. This iterative process reduces the gap between the two distributions interpolated by the sub-models, enabling smaller models with faster training times. Theoretically, we prove a generation guarantee of the proposed flow model regarding the $\\chi^2$-divergence between the generated and true data distributions. Experimentally, we demonstrate the improved training efficiency and competitive generative performance of $\\texttt{LFM}$ compared to FM on the unconditional generation of tabular data and image datasets and its applicability to robotic manipulation policy learning.","url_abs":"https://arxiv.org/abs/2410.02548v2","url_pdf":"https://arxiv.org/pdf/2410.02548v2.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":"local-flow-matching-generative-models","repo_url":"https://github.com/hamrel-cxu/localflowmatching","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"density-estimation","task_name":"Density Estimation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}