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 2403.12969cs.LGquant-ph
收藏

将机器学习与量子张量网络纠缠

Entangling Machine Learning with Quantum Tensor Networks

Sandbox AQ;New York University(纽约大学)

Constantijn van der Poel, Dan Zhao

AI总结:

本文探讨在语言建模中使用张量网络高效表示高维量子态,通过抽象为 Motzkin 自旋链并采用键维度呈次线性扩展的分解核心 MPS,发现模型在训练样本减少时仍保持近乎完美的分类能力与稳定性能。

摘要:

本文探讨了在语言建模中使用张量网络的方法,张量网络能够高效地表示高维量子态。这是对 (van der Poel, 2023) 中所做工作的提炼与延续。为此,我们将问题抽象为对 Motzkin 自旋链进行建模,该链展现出类似于语言中存在的长程关联。Matrix Product State (MPS),也称为张量列车,具有一个随其建模序列长度而扩展的键维度。为了应对这一问题,我们使用了分解核心 MPS,其键维度呈次线性扩展。我们发现,这些张量模型达到了近乎完美的分类能力,并且在有效训练样本数量减少时,仍能保持稳定的性能水平。

英文摘要:

This paper examines the use of tensor networks, which can efficiently represent high-dimensional quantum states, in language modeling. It is a distillation and continuation of the work done in (van der Poel, 2023). To do so, we will abstract the problem down to modeling Motzkin spin chains, which exhibit long-range correlations reminiscent of those found in language. The Matrix Product State (MPS), also known as the tensor train, has a bond dimension which scales as the length of the sequence it models. To combat this, we use the factored core MPS, whose bond dimension scales sub-linearly. We find that the tensor models reach near perfect classifying ability, and maintain a stable level of performance as the number of valid training examples is decreased.

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。

↑