arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.10293quant-phcs.LGcs.NE
收藏

神经张量收缩与深层神经量子态的表达能力

Neural tensor contractions and the expressive power of deep neural quantum states

The Hebrew University of Jerusalem(耶路撒冷希伯来大学);École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院)

Or Sharir, Amnon Shashua, Giuseppe Carleo

摘要:

我们建立了一般张量网络和深度前馈人工神经网络之间的直接联系。我们研究结果的核心是构建神经网络层,这些层可以有效地执行张量收缩,并使用常用的非线性激活函数。由此产生的深度网络具有许多边缘,这些边缘与要近似的张量网络的收缩复杂性密切匹配。在多体量子态的背景下,这一结果表明,神经网络状态具有严格相同或更高的表达能力比实际可用的变分张量网络。作为一个例子,我们表明,所有的矩阵产品状态可以有效地写为神经网络状态的一些边缘多项式的键维数和深度对数的系统大小。相反的情况并不成立,我们的结果意味着存在量子态,它们不能用矩阵乘积态或PEPS有效地表达,但可以用神经网络状态有效地表达。

英文摘要:

We establish a direct connection between general tensor networks and deep feed-forward artificial neural networks. The core of our results is the construction of neural-network layers that efficiently perform tensor contractions, and that use commonly adopted non-linear activation functions. The resulting deep networks feature a number of edges that closely matches the contraction complexity of the tensor networks to be approximated. In the context of many-body quantum states, this result establishes that neural-network states have strictly the same or higher expressive power than practically usable variational tensor networks. As an example, we show that all matrix product states can be efficiently written as neural-network states with a number of edges polynomial in the bond dimension and depth logarithmic in the system size. The opposite instead does not hold true, and our results imply that there exist quantum states that are not efficiently expressible in terms of matrix product states or PEPS, but that are instead efficiently expressible with neural network states.

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。

↑