arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1606.06237stat.MLcs.LG
收藏

在线差分私有张量分解

Online and Differentially-Private Tensor Decomposition

Carnegie Mellon University(卡内基梅隆大学);University of California, Irvine(加利福尼亚大学欧文分校)

Yining Wang, Animashree Anandkumar

摘要:

在本文中,我们解决了许多关键算法的鲁棒性,内存效率和差分隐私张量分解的问题。我们提出了简单的变种张量幂方法,享受这些强大的性能。我们提出了在线张量幂方法的第一个保证,它具有线性内存的要求。此外,我们提出了一个有效的隐私保证噪声校准张量功率方法。在所有这些保证的核心在于仔细的扰动分析,本文中得出的现有的结果显着改善。

英文摘要:

In this paper, we resolve many of the key algorithmic questions regarding robustness, memory efficiency, and differential privacy of tensor decomposition. We propose simple variants of the tensor power method which enjoy these strong properties. We present the first guarantees for online tensor power method which has a linear memory requirement. Moreover, we present a noise calibrated tensor power method with efficient privacy guarantees. At the heart of all these guarantees lies a careful perturbation analysis derived in this paper which improves up on the existing results significantly.

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。

↑