arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.02749cs.DS
收藏

面向张量列车分解的高效杠杆分数采样方法

Efficient Leverage Score Sampling for Tensor Train Decomposition

Vivek Bharadwaj, Beheshteh T. Rakhshan, Osman Asif Malik, Guillaume Rabusseau

AI总结:

本文提出利用TT分解规范形式和精确杠杆分数采样加速ALS算法,以对数时间复杂度高效采样张量,并在合成与真实数据上验证其优于SVD和ALS基线方法。

摘要:

张量列车(TT)分解作为高效压缩高维张量数据的常用工具,在机器学习和量子物理领域得到了广泛应用。本文提出了一种高效算法,用于加速基于精确杠杆分数采样的交替最小二乘(ALS)算法计算TT分解的过程。为此,我们提出了一种数据结构,使我们能够以与张量规模成对数的时间复杂度高效地从张量中进行采样。我们的贡献特别利用了TT分解的规范形式。通过在ALS的每次迭代中保持规范形式,我们可以高效地计算(并从中采样)杠杆分数,从而在求解每个草图化最小二乘问题时实现显著加速。在稠密张量和稀疏张量的合成数据与真实数据上的实验表明,我们的方法优于基于SVD的算法和基于ALS的算法。

英文摘要:

Tensor Train~(TT) decomposition is widely used in the machine learning and quantum physics communities as a popular tool to efficiently compress high-dimensional tensor data. In this paper, we propose an efficient algorithm to accelerate computing the TT decomposition with the Alternating Least Squares (ALS) algorithm relying on exact leverage scores sampling. For this purpose, we propose a data structure that allows us to efficiently sample from the tensor with time complexity logarithmic in the tensor size. Our contribution specifically leverages the canonical form of the TT decomposition. By maintaining the canonical form through each iteration of ALS, we can efficiently compute (and sample from) the leverage scores, thus achieving significant speed-up in solving each sketched least-square problem. Experiments on synthetic and real data on dense and sparse tensors demonstrate that our method outperforms SVD-based and ALS-based algorithms.

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。

↑