arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1701.05039cond-mat.dis-nnquant-ph
收藏

量子多体态的深度神经网络高效表示

Efficient Representation of Quantum Many-body States with Deep Neural Networks

Xun Gao, Lu-Ming Duan

摘要:

量子多体问题的挑战来自于表示大尺度量子态的困难,这通常需要指数数量的参数。最近,在量子多体状态和神经网络表示(\textit{arXiv:1606.02318})之间建立了联系。一个重要的未决问题是深度和浅层神经网络的表征能力是什么,由于深度学习方法的流行,这是一个根本性的问题。在这里,我们给出了一个严格的证明,即深度神经网络可以有效地表示大多数物理状态,包括由任何多项式大小的量子线路或具有多项式大小间隙的许多体哈密顿的基态产生的状态,而通过受限玻尔兹曼机的浅网络不能有效地表示这些状态,除非计算复杂性理论中的多项式层次崩溃。

英文摘要:

The challenge of quantum many-body problems comes from the difficulty to represent large-scale quantum states, which in general requires an exponentially large number of parameters. Recently, a connection has been made between quantum many-body states and the neural network representation (\textit{arXiv:1606.02318}). An important open question is what characterizes the representational power of deep and shallow neural networks, which is of fundamental interest due to popularity of the deep learning methods. Here, we give a rigorous proof that a deep neural network can efficiently represent most physical states, including those generated by any polynomial size quantum circuits or ground states of many body Hamiltonians with polynomial-size gaps, while a shallow network through a restricted Boltzmann machine cannot efficiently represent those states unless the polynomial hierarchy in computational complexity theory collapses.

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。

↑