期刊
PHYSICAL REVIEW LETTERS
卷 130, 期 23, 页码 -出版社
AMER PHYSICAL SOC
DOI: 10.1103/PhysRevLett.130.236401
关键词
-
The ViT architecture, which utilizes the self-attention mechanism to capture long-range correlations, has become the leading model for natural language processing and computer vision tasks. We propose an adaptation of this architecture, called ViT wave function, with complex parameters for variational neural-network states of quantum many-body systems. Applying this idea to the one-dimensional J1-J2 Heisenberg model, we demonstrate that a relatively simple parametrization achieves excellent results for both gapped and gapless phases.
The transformer architecture has become the state-of-art model for natural language processing tasks and, more recently, also for computer vision tasks, thus defining the vision transformer (ViT) architecture. The key feature is the ability to describe long-range correlations among the elements of the input sequences, through the so-called self-attention mechanism. Here, we propose an adaptation of the ViT architecture with complex parameters to define a new class of variational neural-network states for quantum many-body systems, the ViT wave function. We apply this idea to the one-dimensional J1-J2 Heisenberg model, demonstrating that a relatively simple parametrization gets excellent results for both gapped and gapless phases. In this case, excellent accuracies are obtained by a relatively shallow architecture, with a single layer of self-attention, thus largely simplifying the original architecture. Still, the optimization of a deeper structure is possible and can be used for more challenging models, most notably highly frustrated systems in two dimensions. The success of the ViT wave function relies on mixing both local and global operations, thus enabling the study of large systems with high accuracy.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据