arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.03372stat.MLcs.LG
收藏

在线张量学习:计算与统计的权衡、自适应性与最优遗憾

Online Tensor Learning: Computational and Statistical Trade-offs, Adaptivity and Optimal Regret

University of Michigan(密歇根大学);Hong Kong University of Science and Technology(香港科技大学)

Jingyang Li, Jian-Feng Cai, Yang Chen, Dong Xia

AI总结:

本文提出在线黎曼梯度下降算法 oRGrad 及其自适应版本,通过在线更新和自适应步长解决大规模张量学习的高计算与存储问题,在未知时间范围下实现最优遗憾和统计最优误差率。

摘要:

大规模张量学习算法通常计算代价高昂,并且需要存储海量数据。本文提出了一种统一的在线黎曼梯度下降(oRGrad)算法用于张量学习,该算法计算高效、内存消耗显著降低,并且能够在顺序到达的数据流上进行及时预测。该算法适用于线性模型和广义线性模型。如果时间范围 T 已知,oRGrad 通过选择适当的固定步长即可达到统计最优性。我们发现,噪声张量补全尤其受益于在线算法,因为它避免了修剪过程,并保证了逐元素的尖锐统计误差,而这对于离线方法通常在技术上具有挑战性。文中分析了 oRGrad 的遗憾,揭示了一个涉及计算收敛速度、统计误差和遗憾界的有趣三难困境。通过选择合适的常数步长,oRGrad 实现了 $O(T^{1/2})$ 的遗憾。随后我们引入了 adaptive-oRGrad 算法,该算法通过自适应选择步长,无论时间范围是否已知,都能实现最优的 $O(\log T)$ 遗憾。adaptive-oRGrad 算法无需知道时间范围即可达到统计最优误差率。全面的数值模拟验证了我们的理论发现。我们展示了 oRGrad 在使用监测空间天气影响的张量预测因子预测太阳 F10.7 指数方面显著优于其离线对应方法。

英文摘要:

Large tensor learning algorithms are typically computationally expensive and require storing a vast amount of data. In this paper, we propose a unified online Riemannian gradient descent (oRGrad) algorithm for tensor learning, which is computationally efficient, consumes much less memory, and can handle sequentially arriving data while making timely predictions. The algorithm is applicable to both linear and generalized linear models. If the time horizon T is known, oRGrad achieves statistical optimality by choosing an appropriate fixed step size. We find that noisy tensor completion particularly benefits from online algorithms by avoiding the trimming procedure and ensuring sharp entry-wise statistical error, which is often technically challenging for offline methods. The regret of oRGrad is analyzed, revealing a fascinating trilemma concerning the computational convergence rate, statistical error, and regret bound. By selecting an appropriate constant step size, oRGrad achieves an $O(T^{1/2})$ regret. We then introduce the adaptive-oRGrad algorithm, which can achieve the optimal $O(\log T)$ regret by adaptively selecting step sizes, regardless of whether the time horizon is known. The adaptive-oRGrad algorithm can attain a statistically optimal error rate without knowing the horizon. Comprehensive numerical simulations corroborate our theoretical findings. We show that oRGrad significantly outperforms its offline counterpart in predicting the solar F10.7 index with tensor predictors that monitor space weather impacts.

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。

↑