{"title":"求解最优运输问题的高效Halpern加速算法","authors":"Guojun Zhang;Zhexuan Gu;Yancheng Yuan;Defeng Sun","doi":"10.1109/TPAMI.2025.3564353","DOIUrl":null,"url":null,"abstract":"This paper proposes an efficient HOT algorithm for solving the optimal transport (OT) problems with finite supports. We particularly focus on an efficient implementation of the HOT algorithm for the case where the supports are in <inline-formula><tex-math>$\\mathbb {R}^{2}$</tex-math></inline-formula> with ground distances calculated by <inline-formula><tex-math>$L_{2}^{2}$</tex-math></inline-formula>-norm. Specifically, we design a Halpern accelerating algorithm to solve the equivalent reduced model of the discrete OT problem. Moreover, we derive a novel procedure to solve the involved linear systems in the HOT algorithm in linear time complexity. Consequently, we can obtain an <inline-formula><tex-math>$\\varepsilon$</tex-math></inline-formula>-approximate solution to the optimal transport problem with <inline-formula><tex-math>$M$</tex-math></inline-formula> supports in <inline-formula><tex-math>$O(M^{1.5}/\\varepsilon )$</tex-math></inline-formula> flops, which significantly improves the best-known computational complexity. We further propose an efficient procedure to recover an optimal transport plan for the original OT problem based on a solution to the reduced model, thereby overcoming the limitations of the reduced OT model in applications that require the transport plan. We implement the HOT algorithm in PyTorch and extensive numerical results show the superior performance of the HOT algorithm compared to existing state-of-the-art algorithms for solving the OT problems.","PeriodicalId":94034,"journal":{"name":"IEEE transactions on pattern analysis and machine intelligence","volume":"47 8","pages":"6703-6714"},"PeriodicalIF":18.6000,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"HOT: An Efficient Halpern Accelerating Algorithm for Optimal Transport Problems\",\"authors\":\"Guojun Zhang;Zhexuan Gu;Yancheng Yuan;Defeng Sun\",\"doi\":\"10.1109/TPAMI.2025.3564353\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper proposes an efficient HOT algorithm for solving the optimal transport (OT) problems with finite supports. We particularly focus on an efficient implementation of the HOT algorithm for the case where the supports are in <inline-formula><tex-math>$\\\\mathbb {R}^{2}$</tex-math></inline-formula> with ground distances calculated by <inline-formula><tex-math>$L_{2}^{2}$</tex-math></inline-formula>-norm. Specifically, we design a Halpern accelerating algorithm to solve the equivalent reduced model of the discrete OT problem. Moreover, we derive a novel procedure to solve the involved linear systems in the HOT algorithm in linear time complexity. Consequently, we can obtain an <inline-formula><tex-math>$\\\\varepsilon$</tex-math></inline-formula>-approximate solution to the optimal transport problem with <inline-formula><tex-math>$M$</tex-math></inline-formula> supports in <inline-formula><tex-math>$O(M^{1.5}/\\\\varepsilon )$</tex-math></inline-formula> flops, which significantly improves the best-known computational complexity. We further propose an efficient procedure to recover an optimal transport plan for the original OT problem based on a solution to the reduced model, thereby overcoming the limitations of the reduced OT model in applications that require the transport plan. We implement the HOT algorithm in PyTorch and extensive numerical results show the superior performance of the HOT algorithm compared to existing state-of-the-art algorithms for solving the OT problems.\",\"PeriodicalId\":94034,\"journal\":{\"name\":\"IEEE transactions on pattern analysis and machine intelligence\",\"volume\":\"47 8\",\"pages\":\"6703-6714\"},\"PeriodicalIF\":18.6000,\"publicationDate\":\"2025-04-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE transactions on pattern analysis and machine intelligence\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10976595/\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on pattern analysis and machine intelligence","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10976595/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
HOT: An Efficient Halpern Accelerating Algorithm for Optimal Transport Problems
This paper proposes an efficient HOT algorithm for solving the optimal transport (OT) problems with finite supports. We particularly focus on an efficient implementation of the HOT algorithm for the case where the supports are in $\mathbb {R}^{2}$ with ground distances calculated by $L_{2}^{2}$-norm. Specifically, we design a Halpern accelerating algorithm to solve the equivalent reduced model of the discrete OT problem. Moreover, we derive a novel procedure to solve the involved linear systems in the HOT algorithm in linear time complexity. Consequently, we can obtain an $\varepsilon$-approximate solution to the optimal transport problem with $M$ supports in $O(M^{1.5}/\varepsilon )$ flops, which significantly improves the best-known computational complexity. We further propose an efficient procedure to recover an optimal transport plan for the original OT problem based on a solution to the reduced model, thereby overcoming the limitations of the reduced OT model in applications that require the transport plan. We implement the HOT algorithm in PyTorch and extensive numerical results show the superior performance of the HOT algorithm compared to existing state-of-the-art algorithms for solving the OT problems.