arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1010.3043math.NAcs.NAstat.COstat.ME
收藏

使张量分解对非高斯噪声鲁棒

Making Tensor Factorizations Robust to Non-Gaussian Noise

Rice University(莱斯大学);Sandia National Laboratories(桑迪亚国家实验室)

Eric C. Chi, Tamara G. Kolda

AI总结:

针对CP张量分解在非高斯噪声下敏感的问题,提出基于1-范数的损失函数,并设计交替最小化-最大化算法进行拟合。

摘要:

张量是多维数组,Candecomp/Parafac (CP) 张量分解已在许多不同领域得到应用。CP 模型通常使用最小二乘目标函数进行拟合,这是在独立同分布高斯噪声假设下的最大似然估计。我们证明该损失函数实际上对非高斯噪声高度敏感。因此,我们提出一种基于1-范数的损失函数,因为它可以同时处理高斯和严重非高斯扰动。我们还提出了一种交替最小化-最大化算法,用于使用我们提出的损失函数拟合 CP 模型。

英文摘要:

Tensors are multi-way arrays, and the Candecomp/Parafac (CP) tensor factorization has found application in many different domains. The CP model is typically fit using a least squares objective function, which is a maximum likelihood estimate under the assumption of i.i.d. Gaussian noise. We demonstrate that this loss function can actually be highly sensitive to non-Gaussian noise. Therefore, we propose a loss function based on the 1-norm because it can accommodate both Gaussian and grossly non-Gaussian perturbations. We also present an alternating majorization-minimization algorithm for fitting a CP model using our proposed loss function.

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。

↑