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 1706.08672cs.LGcs.DSstat.ML
收藏

快速鲁棒的张量分解及其在字典学习中的应用

Fast and robust tensor decomposition with applications to dictionary learning

UC Berkeley(加州大学伯克利分校);Cornell University(康奈尔大学)

Tselil Schramm, David Steurer

摘要:

我们开发快速谱算法张量分解,匹配的最知名的多项式时间算法的鲁棒性保证这个问题的基础上的平方和(SOS)半定规划层次。我们的算法可以分解一个4-张量与$n$ -维正交分量的存在误差与恒定的谱范数(当被视为一个$n^2$ -由$n^2$矩阵)。运行时间为$n^5$,它与输入大小$n^4$接近线性。我们还获得了类似的运行时间学习稀疏使用的正交字典的算法,即使特征表示具有恒定的相对稀疏性和非独立坐标。以前唯一的多项式时间算法来解决这些问题是基于解决大型半定规划。相比之下,我们的算法很容易直接实现,是基于光谱投影和张量模式重排。或者工作的灵感来自最近的霍普金斯,施拉姆,施,和Steurer(STOC'16),显示如何快速谱算法可以实现平均情况下的SOS问题的保证。在这项工作中,我们介绍了一般的技术来捕捉SOS的最坏情况下的问题的保证。

英文摘要:

We develop fast spectral algorithms for tensor decomposition that match the robustness guarantees of the best known polynomial-time algorithms for this problem based on the sum-of-squares (SOS) semidefinite programming hierarchy. Our algorithms can decompose a 4-tensor with $n$-dimensional orthonormal components in the presence of error with constant spectral norm (when viewed as an $n^2$-by-$n^2$ matrix). The running time is $n^5$ which is close to linear in the input size $n^4$. We also obtain algorithms with similar running time to learn sparsely-used orthogonal dictionaries even when feature representations have constant relative sparsity and non-independent coordinates. The only previous polynomial-time algorithms to solve these problem are based on solving large semidefinite programs. In contrast, our algorithms are easy to implement directly and are based on spectral projections and tensor-mode rearrangements. Or work is inspired by recent of Hopkins, Schramm, Shi, and Steurer (STOC'16) that shows how fast spectral algorithms can achieve the guarantees of SOS for average-case problems. In this work, we introduce general techniques to capture the guarantees of SOS for worst-case problems.

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。

↑