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 1802.03936cs.LG
收藏

关于超三次Quantization散列中对旋转的要求

On the Needs for Rotations in Hypercubic Quantization Hashing

CEA(法国原子能和替代能源委员会);Université Paris-Dauphine, PSL Research University(巴黎多芬大学(PSL研究型大学));Google Brain Robotics(谷歌大脑机器人部门)

Anne Morvan, Antoine Souloumiac, Krzysztof Choromanski, Cédric Gouy-Pailler, Jamal Atif

摘要:

本文的目的是赋予著名的家庭超立方量化哈希方法的理论保证。在超立方量化中,在降维之后应用合适的(随机或学习的)旋转已经被实验证明可以提高最近邻搜索问题中的结果精度。在本文中,我们证明了这些旋转的使用是最佳的一些温和的假设下:得到最佳的二进制草图是等同于应用旋转均匀化数据点之间的协方差矩阵的对角线。此外,对于两个封闭点,具有不同的二进制草图的概率的上限由数据点之间的初始距离的因子。放松这些假设,我们得到一个一般的随机矩阵的浓度结果。我们还提供了一些实验来说明这些理论观点,并比较了一组算法在批处理和在线设置。

英文摘要:

The aim of this paper is to endow the well-known family of hypercubic quantization hashing methods with theoretical guarantees. In hypercubic quantization, applying a suitable (random or learned) rotation after dimensionality reduction has been experimentally shown to improve the results accuracy in the nearest neighbors search problem. We prove in this paper that the use of these rotations is optimal under some mild assumptions: getting optimal binary sketches is equivalent to applying a rotation uniformizing the diagonal of the covariance matrix between data points. Moreover, for two closed points, the probability to have dissimilar binary sketches is upper bounded by a factor of the initial distance between the data points. Relaxing these assumptions, we obtain a general concentration result for random matrices. We also provide some experiments illustrating these theoretical points and compare a set of algorithms in both the batch and online settings.

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。

↑