arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.05495cs.LG
收藏

通过自由能最小化的距离度量学习

Distance Metric Learning through Minimization of the Free Energy

Universidade Federal de Pernambuco(伯南布哥联邦大学);Universidade Federal Rural de Pernambuco(伯南布哥联邦农村大学)

Dusan Stosic, Darko Stosic, Teresa B. Ludermir, Borko Stosic

摘要:

在过去的几十年里,距离度量学习在解决机器学习和模式识别问题方面吸引了很多兴趣。在这项工作中,我们提出了一个简单的方法,从统计物理学的概念,学习最佳的距离度量给定的问题。我们制定的任务作为一个典型的统计物理问题:模式之间的距离代表的组成部分的物理系统和目标函数对应的能量。然后,我们将问题表示为复杂系统的自由能的最小化,这相当于距离度量学习。就像物理学中的许多问题一样,我们提出了一种基于Metropolis Monte Carlo的方法来找到最佳距离度量。这提供了一种自然的方式来学习距离度量,其中学习过程可以直观地看作是拉伸和旋转度量空间,直到满足某些启发式。我们提出的方法可以处理各种各样的约束,包括那些虚假的局部极小值。该方法与来自邻域分量分析(NCA)的随机最近邻的效果令人惊讶地好。人工和真实世界的数据集上的实验结果显示出明显的优越性,在一些国家的最先进的距离度量学习方法的最近邻分类。

英文摘要:

Distance metric learning has attracted a lot of interest for solving machine learning and pattern recognition problems over the last decades. In this work we present a simple approach based on concepts from statistical physics to learn optimal distance metric for a given problem. We formulate the task as a typical statistical physics problem: distances between patterns represent constituents of a physical system and the objective function corresponds to energy. Then we express the problem as a minimization of the free energy of a complex system, which is equivalent to distance metric learning. Much like for many problems in physics, we propose an approach based on Metropolis Monte Carlo to find the best distance metric. This provides a natural way to learn the distance metric, where the learning process can be intuitively seen as stretching and rotating the metric space until some heuristic is satisfied. Our proposed method can handle a wide variety of constraints including those with spurious local minima. The approach works surprisingly well with stochastic nearest neighbors from neighborhood component analysis (NCA). Experimental results on artificial and real-world data sets reveal a clear superiority over a number of state-of-the-art distance metric learning methods for nearest neighbors classification.

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。

↑