{"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/deeplm-large-scale-nonlinear-least-squares-on","title":"DeepLM: Large-Scale Nonlinear Least Squares on Deep Learning Frameworks Using Stochastic Domain Decomposition","arxiv_id":null,"date":"2021-06-19","proceeding":"CVPR 2021 1","authors":["Jingwei Huang","Shan Huang","Mingwei Sun"],"abstract":"    We propose a novel approach for large-scale nonlinear least squares problems based on deep learning frameworks. Nonlinear least squares are commonly solved with the Levenberg-Marquardt (LM) algorithm for fast convergence. We implement a general and efficient LM solver on a deep learning framework by designing a new backward jacobian network to enable automatic sparse jacobian matrix computation. Furthermore, we introduce a stochastic domain decomposition approach that enables batched optimization and preserves convergence for large problems. We evaluate our method by solving bundle adjustment as a fundamental problem. Experiments show that our optimizer significantly outperforms the state-of-the-art solutions and existing deep learning solvers considering quality, efficiency, and memory. Our stochastic domain decomposition enables distributed optimization, consumes little memory and time, and achieves similar quality compared to a global solver. As a result, our solver effectively solves nonlinear least squares on an extremely large scale. We will make the code publicly available on publication.    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2021/html/Huang_DeepLM_Large-Scale_Nonlinear_Least_Squares_on_Deep_Learning_Frameworks_Using_CVPR_2021_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2021/papers/Huang_DeepLM_Large-Scale_Nonlinear_Least_Squares_on_Deep_Learning_Frameworks_Using_CVPR_2021_paper.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":"deeplm-large-scale-nonlinear-least-squares-on","repo_url":"https://github.com/hjwdzh/DeepLM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"deeplm-large-scale-nonlinear-least-squares-on","repo_url":"https://github.com/mindspore-ai/models/tree/master/research/3d/DeepLM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"distributed-optimization","task_name":"Distributed Optimization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}