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 2305.02460cs.LGphysics.comp-ph
收藏

张量化流:一种用于变分推断的工具

Tensorizing flows: a tool for variational inference

University of Chicago(芝加哥大学);University of California, Berkeley(加州大学伯克利分校)

Yuehaw Khoo, Michael Lindsey, Hongli Zhao

AI总结:

针对变分推断中归一化流的高斯参考分布难学习多峰分布的问题,提出用矩阵乘积态/张量列张量网络构建的参考分布替代高斯分布的扩展方法,实验证明结合效果优于单独使用两种工具。

摘要:

得益于深度神经网络的强大表达能力,归一化流在生成建模(即基于有限训练样本数据集学习从分布中抽取新样本的任务)中取得了惊人的成功。归一化流也已成功应用于变分推断,该任务中研究者尝试基于分布的对数似然或能量函数表达式而非数据来学习采样器。在变分推断中,归一化流内部使用的参考高斯分布的单峰性会给多峰分布的学习带来困难。我们提出了一种归一化流的扩展方法,将其中的高斯参考分布替换为通过张量网络(具体为矩阵乘积态或张量列)构建的参考分布。我们证明,在高难度变分推断任务上将流与张量网络相结合,其效果优于单独使用两种方法中的任意一种。

英文摘要:

Fueled by the expressive power of deep neural networks, normalizing flows have achieved spectacular success in generative modeling, or learning to draw new samples from a distribution given a finite dataset of training samples. Normalizing flows have also been applied successfully to variational inference, wherein one attempts to learn a sampler based on an expression for the log-likelihood or energy function of the distribution, rather than on data. In variational inference, the unimodality of the reference Gaussian distribution used within the normalizing flow can cause difficulties in learning multimodal distributions. We introduce an extension of normalizing flows in which the Gaussian reference is replaced with a reference distribution that is constructed via a tensor network, specifically a matrix product state or tensor train. We show that by combining flows with tensor networks on difficult variational inference tasks, we can improve on the results obtained by using either tool without the other.

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。

↑