论文标题
TTML：用于一般监督机器学习的张量火车
TTML: tensor trains for general supervised machine learning
论文作者
论文摘要
这项工作提出了一种基于张量火车（TT）的监督机器学习（ML）的新型通用估计器。估算器使用TTS参数化离散功能，然后在张量完成问题的形式下使用Riemannian梯度下降进行优化。由于这种优化对初始化很敏感，因此事实证明，使用其他ML估计器来初始化至关重要。与许多其他ML估计器相比，这会导致具有较低存储器使用的竞争，快速的ML估计器，例如用于初始化的估计器。
This work proposes a novel general-purpose estimator for supervised machine learning (ML) based on tensor trains (TT). The estimator uses TTs to parametrize discretized functions, which are then optimized using Riemannian gradient descent under the form of a tensor completion problem. Since this optimization is sensitive to initialization, it turns out that the use of other ML estimators for initialization is crucial. This results in a competitive, fast ML estimator with lower memory usage than many other ML estimators, like the ones used for the initialization.
