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 2311.06358cs.LGmath.COmath.CTmath.RTstat.ML
收藏

紧矩阵量子群等变神经网络

Compact Matrix Quantum Group Equivariant Neural Networks

Department of Computing, Imperial College London, United Kingdom(计算机系,伦敦帝国学院,英国)

Edward Pearce-Crump

AI总结:

本文提出紧矩阵量子群等变神经网络,以处理非交换几何数据,并刻画简单紧矩阵量子群的权重矩阵,获得新的等变权重矩阵表征。

摘要:

群等变神经网络已被证明在数据位于经典几何空间且具有明确群对称性的广泛任务中建模有效。然而,这些网络不适用于学习位于非交换几何中的数据,该几何由非交换$C^{*}$-代数正式描述,因为紧矩阵群上连续函数的$C^{*}$-代数是交换的。为解决此限制,我们推导出一种新型等变神经网络的存在性,称为紧矩阵量子群等变神经网络,其编码由紧矩阵量子群描述的对称性。我们刻画了这些神经网络中出现的权重矩阵,针对由集合划分定义的简单紧矩阵量子群。由此,我们获得了机器学习文献中此前未出现的一些紧矩阵群的等变权重矩阵的新刻画。

英文摘要:

Group equivariant neural networks have proven effective in modelling a wide range of tasks where the data lives in a classical geometric space and exhibits well-defined group symmetries. However, these networks are not suitable for learning from data that lives in a non-commutative geometry, described formally by non-commutative $C^{*}$-algebras, since the $C^{*}$-algebra of continuous functions on a compact matrix group is commutative. To address this limitation, we derive the existence of a new type of equivariant neural network, called compact matrix quantum group equivariant neural networks, which encode symmetries that are described by compact matrix quantum groups. We characterise the weight matrices that appear in these neural networks for the easy compact matrix quantum groups, which are defined by set partitions. As a result, we obtain new characterisations of equivariant weight matrices for some compact matrix groups that have not appeared previously in the machine learning literature.

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。

↑