arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1507.07974stat.MLcs.ITcs.LGmath.IT
收藏

一种在线张量预测算法

An algorithm for online tensor prediction

Microsoft(微软);Tufts University(塔夫茨大学)

John Pothier, Josh Girson, Shuchin Aeron

摘要:

我们提出了一种新的方法在线预测和学习张量($N$ -路阵列,$N >2$)从连续的测量。我们专注于3-D张量的特定情况下,并利用最近发展的结构化张量分解的框架中提出的[1]。在这个框架中,可以将三维张量视为线性算子,并以自然的方式将秩和正定性的概念适当地推广到张量。使用这些概念,我们提出了一个推广的矩阵指数梯度下降算法[2]的张量指数梯度下降算法,使用的概念冯诺依曼发散张量的扩展。然后按照与[3]类似的构造,我们利用该算法提出了一个在线学习和预测具有可证明后悔保证的张量的算法。模拟结果上的半合成数据集的评级演变的时间在当地的影响下,在社会网络。结果表明,优越的性能相比,其他(在线)凸张量完成方法。

英文摘要:

We present a new method for online prediction and learning of tensors ($N$-way arrays, $N >2$) from sequential measurements. We focus on the specific case of 3-D tensors and exploit a recently developed framework of structured tensor decompositions proposed in [1]. In this framework it is possible to treat 3-D tensors as linear operators and appropriately generalize notions of rank and positive definiteness to tensors in a natural way. Using these notions we propose a generalization of the matrix exponentiated gradient descent algorithm [2] to a tensor exponentiated gradient descent algorithm using an extension of the notion of von-Neumann divergence to tensors. Then following a similar construction as in [3], we exploit this algorithm to propose an online algorithm for learning and prediction of tensors with provable regret guarantees. Simulations results are presented on semi-synthetic data sets of ratings evolving in time under local influence over a social network. The result indicate superior performance compared to other (online) convex tensor completion methods.

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。

↑