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 2101.09184cs.LG
收藏

用于多维数据预测建模的张量训练网络

Tensor-Train Networks for Learning Predictive Modeling of Multidimensional Data

University of Campinas(坎皮纳斯大学);Skolkovo Institute of Science and Technology (SKOLTECH)(斯科尔科沃科学技术学院);Nicolaus Copernicus University(哥白尼大学)

M. Nazareth da Costa, R. Attux, A. Cichocki, J. M. T. Romano

摘要:

在这项工作中,我们首先应用训练张量(TT)网络来构建经典多层感知器的紧凑表示,表示减少高达95%的系数。张量模型和标准的多层神经网络之间的比较分析也进行了预测的Mackey-Glass噪声混沌时间序列和纳斯达克指数的背景下。我们表明,多维回归模型的权重可以通过TT网络学习,TT权重的优化对系数初始化和超参数设置的影响具有更强的鲁棒性。此外,提出了一种基于交替最小二乘法的有效算法,用于近似TT格式的权重,减少了计算量,比广泛应用于优化神经网络的众所周知的自适应学习方法算法提供了更快的收敛速度。

英文摘要:

In this work, we firstly apply the Train-Tensor (TT) networks to construct a compact representation of the classical Multilayer Perceptron, representing a reduction of up to 95% of the coefficients. A comparative analysis between tensor model and standard multilayer neural networks is also carried out in the context of prediction of the Mackey-Glass noisy chaotic time series and NASDAQ index. We show that the weights of a multidimensional regression model can be learned by means of TT network and the optimization of TT weights is a more robust to the impact of coefficient initialization and hyper-parameter setting. Furthermore, an efficient algorithm based on alternating least squares has been proposed for approximating the weights in TT-format with a reduction of computational calculus, providing a much faster convergence than the well-known adaptive learning-method algorithms, widely applied for optimizing neural networks.

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。

↑