arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.06338cs.LGmath.OCstat.ML
收藏

理解用于模式恢复的近似和展开字典学习

Understanding approximate and unrolled dictionary learning for pattern recovery

Université Paris-Saclay(巴黎萨克雷大学);Inria(法国国家信息与自动化研究所);CEA(法国原子能委员会);L2S(L2S实验室);Université Paris-Saclay–CNRS–CentraleSupelec(巴黎萨克雷大学–法国国家科学研究中心–中央理工高等电力学院);CentraleSupelec(中央理工高等电力学院)

Benoît Malézieux, Thomas Moreau, Matthieu Kowalski

摘要:

字典学习包括从噪声数据中找到稀疏表示,并且是对信号进行数据驱动先验知识编码的常用方法。交替最小化(AM)是底层优化的标准,其中梯度下降步骤与稀疏编码过程交替。这种方法的主要缺点是其高昂的计算成本,使其不实用的大型现实世界的数据集。本文研究了一种基于展开的字典学习的近似公式,并将其与交替最小化进行比较,以找到速度和精度之间的最佳权衡。我们分析了这两种方法中梯度估计的渐近性态和收敛速度。我们表明,展开执行更好的内部问题解决方案的支持,并在第一次迭代。最后,我们应用展开模式学习脑磁图(MEG)的帮助下,一个随机算法和性能比较的国家的最先进的方法。

英文摘要:

Dictionary learning consists of finding a sparse representation from noisy data and is a common way to encode data-driven prior knowledge on signals. Alternating minimization (AM) is standard for the underlying optimization, where gradient descent steps alternate with sparse coding procedures. The major drawback of this method is its prohibitive computational cost, making it unpractical on large real-world data sets. This work studies an approximate formulation of dictionary learning based on unrolling and compares it to alternating minimization to find the best trade-off between speed and precision. We analyze the asymptotic behavior and convergence rate of gradients estimates in both methods. We show that unrolling performs better on the support of the inner problem solution and during the first iterations. Finally, we apply unrolling on pattern learning in magnetoencephalography (MEG) with the help of a stochastic algorithm and compare the performance to a state-of-the-art method.

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。

↑