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 1910.09652stat.MLcs.LG
收藏

Kernelized Wasserstein自然渐变

Kernelized Wasserstein Natural Gradient

Gatsby Computational Neuroscience Unit(盖茨比计算神经科学研究室);University College London(伦敦大学学院);University of California, Los Angeles(加利福尼亚大学洛杉矶分校);Max Planck Institute for Mathematics in the Sciences(马克斯·普朗克数学科学研究所)

Michael Arbel, Arthur Gretton, Wuchen Li, Guido Montufar

摘要:

许多机器学习问题可以表示为在概率分布的参数族上优化一些代价泛函。使用自然梯度方法来解决这样的优化问题通常是有益的。这些方法对族的参数化是不变的,因此可以产生更有效的优化。不幸的是,计算自然梯度是具有挑战性的,因为它需要在每次迭代时对高维矩阵进行求逆。我们提出了一个一般的框架来近似自然梯度的Wasserstein度量,利用一个双重制定的度量限制到一个再生核希尔伯特空间。我们的方法导致梯度方向的估计,可以权衡精度和计算成本,理论保证。我们在简单的例子中验证了它的准确性,并展示了在Cifar10和Cifar100的分类任务中使用这种估计的优势。

英文摘要:

Many machine learning problems can be expressed as the optimization of some cost functional over a parametric family of probability distributions. It is often beneficial to solve such optimization problems using natural gradient methods. These methods are invariant to the parametrization of the family, and thus can yield more effective optimization. Unfortunately, computing the natural gradient is challenging as it requires inverting a high dimensional matrix at each iteration. We propose a general framework to approximate the natural gradient for the Wasserstein metric, by leveraging a dual formulation of the metric restricted to a Reproducing Kernel Hilbert Space. Our approach leads to an estimator for gradient direction that can trade-off accuracy and computational cost, with theoretical guarantees. We verify its accuracy on simple examples, and show the advantage of using such an estimator in classification tasks on Cifar10 and Cifar100 empirically.

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。

↑