HOT:一种用于最优传输问题的高效Halpern加速算法
HOT: An Efficient Halpern Accelerating Algorithm for Optimal Transport Problems
AI总结:
本文针对有限支撑集的最优传输问题提出HOT算法,通过Halpern加速及线性时间求解线性系统的新过程,以$O(M^{1.5}/\varepsilon)$复杂度获$\varepsilon$-近似解,还能恢复传输计划,在PyTorch中实现且性能优于现有算法。
摘要:
本文提出一种高效的HOT算法,用于求解具有有限支撑集的最优传输(OT)问题。我们特别关注支撑集位于$\mathbb{R}^2$且地距离由$L_2^2$-范数计算的情况,以实现HOT算法的高效执行。具体而言,我们设计了一种Halpern加速算法来求解离散OT问题的等效简化模型。此外,我们推导了一种新的过程,能以线性时间复杂度求解HOT算法中涉及的线性系统。因此,对于具有$M$个支撑集的最优传输问题,我们可在$O(M^{1.5}/\varepsilon)$次浮点运算内获得$\varepsilon$-近似解,显著改进了现有最佳计算复杂度。我们还提出一种高效过程,基于简化模型的解恢复原始OT问题的最优传输计划,从而克服简化OT模型在需要传输计划的应用中的局限性。我们在PyTorch中实现了HOT算法,大量数值结果表明,与现有求解OT问题的最先进算法相比,HOT算法性能更优。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。