arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.00089cs.LGcs.AIstat.ML
收藏

张量序列密度估计

Tensor-Train Density Estimation

Skolkovo Institute of Science and Technology(斯科尔科沃科学技术研究所)

Georgii S. Novikov, Maxim E. Panov, Ivan V. Oseledets

摘要:

从样本中估计概率密度函数是统计学和机器学习的核心问题之一。基于现代神经网络的模型可以学习高维分布,但在超参数选择方面存在问题,并且在训练和推理过程中往往容易出现不稳定性。我们提出了一种新的有效的基于张量训练的密度估计模型(TTDE)。这样的密度参数化允许精确采样,计算累积和边缘密度函数,以及配分函数。它也有非常直观的超参数。我们开发了一个有效的非对抗性训练过程TTDE的基础上黎曼优化。实验结果表明,所提出的方法在密度估计和采样任务的竞争性能,而TTDE显着优于竞争对手的训练速度。

英文摘要:

Estimation of probability density function from samples is one of the central problems in statistics and machine learning. Modern neural network-based models can learn high dimensional distributions but have problems with hyperparameter selection and are often prone to instabilities during training and inference. We propose a new efficient tensor train-based model for density estimation (TTDE). Such density parametrization allows exact sampling, calculation of cumulative and marginal density functions, and partition function. It also has very intuitive hyperparameters. We develop an efficient non-adversarial training procedure for TTDE based on the Riemannian optimization. Experimental results demonstrate the competitive performance of the proposed method in density estimation and sampling tasks, while TTDE significantly outperforms competitors in training speed.

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。

↑