arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.04088math.OCmath.APmath.PR
收藏

二次正则化线性规划的定量收敛性

Quantitative Convergence of Quadratically Regularized Linear Programs

Alberto González-Sanz, Marcel Nutz

AI总结:

本研究量化了二次正则化线性规划解的收敛性,给出了正则化参数的精确阈值及阈值前后的次优性界限,并应用于最优输运,揭示了与数据点数的依赖关系。

摘要:

具有二次正则化的线性规划因其在最优输运中的应用而重新引起关注:与熵正则化不同,平方范数惩罚会产生最优输运耦合的稀疏近似。众所周知,当正则化参数趋于零时,任意多面体上的二次正则化线性规划的解平稳收敛到线性规划的最小范数解。然而,该结果仅是定性的。我们的主要结果通过指定正则化参数的精确阈值来量化收敛性,超过该阈值后,正则化解也求解线性规划。此外,我们限定了在阈值之前正则化解的次优性。这些结果辅以在大正则化情形下的收敛速率。我们将一般结果应用于最优输运设置,揭示了阈值和次优性如何依赖于数据点的数量。

英文摘要:

Linear programs with quadratic regularization are attracting renewed interest due to their applications in optimal transport: unlike entropic regularization, the squared-norm penalty gives rise to sparse approximations of optimal transport couplings. It is well known that the solution of a quadratically regularized linear program over any polytope converges stationarily to the minimal-norm solution of the linear program when the regularization parameter tends to zero. However, that result is merely qualitative. Our main result quantifies the convergence by specifying the exact threshold for the regularization parameter, after which the regularized solution also solves the linear program. Moreover, we bound the suboptimality of the regularized solution before the threshold. These results are complemented by a convergence rate for the regime of large regularization. We apply our general results to the setting of optimal transport, where we shed light on how the threshold and suboptimality depend on the number of data points.

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。

↑