arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.15338stat.MLcs.LG
收藏

非负张量的多体近似

Many-body Approximation for Non-negative Tensors

RIKEN AIP(理化学研究所革新智能统合研究中心);National Institute of Informatics(国立情报学研究所);SOKENDAI(综合研究大学院大学);Osaka University(大阪大学)

Kazu Ghalamkari, Mahito Sugiyama, Yoshinobu Kawahara

AI总结:

本文提出多体近似方法,通过基于能量的概率建模分解非负张量,以KL散度全局优化替代低秩假设,并揭示其与低秩近似的关系,在张量补全与近似任务中验证了有效性。

摘要:

我们提出了一种分解非负张量的替代方法,称为多体近似。传统的分解方法假设表示具有低秩性,这导致全局优化和目标秩选择方面的困难。我们通过对张量进行基于能量的建模来避免这些问题,其中张量及其模态分别对应于概率分布和随机变量。我们的模型可以通过考虑变量(即模态)之间的相互作用,在KL散度最小化方面进行全局优化,这种相互作用可以比秩更直观地进行调节。此外,我们将模态之间的相互作用可视化为张量网络,并揭示了多体近似与低秩近似之间的非平凡关系。我们证明了我们的方法在张量补全和近似中的有效性。

英文摘要:

We present an alternative approach to decompose non-negative tensors, called many-body approximation. Traditional decomposition methods assume low-rankness in the representation, resulting in difficulties in global optimization and target rank selection. We avoid these problems by energy-based modeling of tensors, where a tensor and its mode correspond to a probability distribution and a random variable, respectively. Our model can be globally optimized in terms of the KL divergence minimization by taking the interaction between variables (that is, modes), into account that can be tuned more intuitively than ranks. Furthermore, we visualize interactions between modes as tensor networks and reveal a nontrivial relationship between many-body approximation and low-rank approximation. We demonstrate the effectiveness of our approach in tensor completion and approximation.

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。

↑