arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.05101cs.LGcs.DSstat.ML
收藏

张量化随机投影

Tensorized Random Projections

Purdue University(普渡大学);Université de Montréal(蒙特利尔大学)

Beheshteh T. Rakhshan, Guillaume Rabusseau

摘要:

我们介绍了一种新的随机投影技术,有效地降低非常高维张量的维数。基于高斯随机投影和Johnson-Lindenstrauss变换(JLT)的经典结果,我们提出了两种分别依赖于张量训练(TT)和CP分解格式的张量化随机投影映射。这两个映射提供了非常低的内存需求,并且当输入是以CP或TT格式给出的低阶张量时可以有效地应用。我们的理论分析表明,JLT中的稠密高斯矩阵可以用一个低秩张量来代替,该张量以压缩的形式隐式地表示,并带有随机因子,同时仍然近似地保持投影输入的欧几里得距离。此外,我们的研究结果表明,TT格式是实质上优于CP方面的随机投影的大小需要达到相同的失真率。在合成数据上的实验验证了理论分析的正确性,并证明了TT分解的优越性。

英文摘要:

We introduce a novel random projection technique for efficiently reducing the dimension of very high-dimensional tensors. Building upon classical results on Gaussian random projections and Johnson-Lindenstrauss transforms~(JLT), we propose two tensorized random projection maps relying on the tensor train~(TT) and CP decomposition format, respectively. The two maps offer very low memory requirements and can be applied efficiently when the inputs are low rank tensors given in the CP or TT format. Our theoretical analysis shows that the dense Gaussian matrix in JLT can be replaced by a low-rank tensor implicitly represented in compressed form with random factors, while still approximately preserving the Euclidean distance of the projected inputs. In addition, our results reveal that the TT format is substantially superior to CP in terms of the size of the random projection needed to achieve the same distortion ratio. Experiments on synthetic data validate our theoretical analysis and demonstrate the superiority of the TT decomposition.

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。

↑