arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2102.12731cs.LGstat.ML
收藏

利用Quantization改进近似最优传输距离

Improving Approximate Optimal Transport Distances using Quantization

MIT CSAIL(麻省理工学院计算机科学与人工智能实验室);INRIA(法国国家信息与自动化研究所);IBM Watson AI Lab(IBM沃森人工智能实验室)

Gaspard Beugnot, Aude Genevay, Kristjan Greenewald, Justin Solomon

摘要:

最优传输(OT)是机器学习中一种常用的几何比较概率度量的工具,但它带来了大量的计算负担。用于计算OT距离的线性规划算法在输入的大小上按立方缩放,使得OT在大样本范围内不切实际。我们引入了一个实用的算法,它依赖于一个量化的步骤,以估计成本低廉的样本访问措施之间的OT距离。我们还提供了我们的算法的一个变种,以提高近似求解器的性能,专注于那些熵正则化运输。我们给出了理论上的保证,这个量化步骤的好处,并显示实验表明,它在实践中表现良好,提供了一个实用的近似算法,可用于作为一个下拉式替代现有的OT估计。

英文摘要:

Optimal transport (OT) is a popular tool in machine learning to compare probability measures geometrically, but it comes with substantial computational burden. Linear programming algorithms for computing OT distances scale cubically in the size of the input, making OT impractical in the large-sample regime. We introduce a practical algorithm, which relies on a quantization step, to estimate OT distances between measures given cheap sample access. We also provide a variant of our algorithm to improve the performance of approximate solvers, focusing on those for entropy-regularized transport. We give theoretical guarantees on the benefits of this quantization step and display experiments showing that it behaves well in practice, providing a practical approximation algorithm that can be used as a drop-in replacement for existing OT estimators.

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。

↑