Entropic regularization provides a generalization of the original optimal transport problem. It introduces a penalty term defined by the Kullback-Leibler divergence, making the problem more tractable via the celebrated Sinkhorn algorithm. Replacing the Kullback-Leibler divergence with a general $f$-divergence leads to a natural generalization. The case of divergences defined by superlinear functions was recently studied by Di Marino and Gerolin. Using convex analysis, we extend the theory developed so far to include all $f$-divergences defined by functions of Legendre type, and prove that under some mild conditions, strong duality holds, optimums in both the primal and dual problems are attained, the generalization of the $c$-transform is well-defined, and we give sufficient conditions for the generalized Sinkhorn algorithm to converge to an optimal solution. We propose a practical algorithm for computing an approximate solution of the optimal transport problem with $f$-divergence regularization via the generalized Sinkhorn algorithm. Finally, we present experimental results on synthetic 2-dimensional data, demonstrating the effects of using different $f$-divergences for regularization, which influences convergence speed, numerical stability and sparsity of the optimal coupling.
翻译:内地规范化为原始最佳运输问题的概括化提供了原始最佳运输问题的概括化。 它引入了由 Kullback- Leiber 差异定义的处罚术语, 使得这个问题通过著名的辛克霍恩算法更加容易处理。 用一般美元波动法取代 Kullback- Leiber 差异, 导致自然化。 由超线函数定义的差异案例最近由迪马利诺和杰罗林进行了研究。 我们利用 convex 分析, 将迄今所开发的理论扩展至包括所有由图例类型函数定义的美元- diverences, 并证明在某些温和条件下, 强大的双重性存在, 最优化的原始和双重问题已经达到, 美化的美元- 变异形式得到了很好的界定, 我们为通用的辛克霍恩算法将最佳运输问题计算出一个大致的解决方案。 我们提出一个实用的算法, 通过通用的辛克霍恩算法, 通过通用的Sinkhorn算法, 来计算出最优化的美元- diverence 正规化的运输问题。 最后, 我们展示了合成二维数据的实验结果, 的双重数据, 的趋同值数据, 展示了稳定化, 的趋同性, 的趋同性, 和最高的汇率的趋和最高的摩合。