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 2501.04833math.OC
收藏

用于块项张量分解的多步惯性加速双随机梯度方法

Multi-step Inertial Accelerated Doubly Stochastic Gradient Methods for Block Term Tensor Decomposition

Zehui Liu, Qingsong Wang, Chunfeng Cui

AI总结:

针对带正则项的秩-$(L_r,L_r,1)$块项张量分解,本文提出多步惯性加速双随机方法 Midas-LL1 及方差缩减估计框架,证明其收敛性与 $\mathcal{O}(\varepsilon^{-2})$ 迭代复杂度,并在实验中优于现有方法。

摘要:

本文研究了一个针对多块变量、将可微非凸函数与不可微函数相结合的特定优化问题,该问题与求解带正则项的多线性秩-$(L_r,L_r,1)$块项张量分解模型尤为相关。现有算法往往面临单次迭代复杂度高和收敛缓慢的问题,为此本文采用一种统一的多步惯性加速双随机梯度下降方法,专为结构化秩-$(L_r,L_r,1)$张量分解定制,称为 Midas-LL1。我们还提出了一个扩展的多步方差缩减随机估计器框架。在这一新框架下的分析表明,所提算法在一定条件下具有子序列收敛性和序列收敛性,并阐明了子序列的次线性收敛速率,说明 Midas-LL1 算法达到 $\varepsilon$-稳定点在期望意义下至多需要 $\mathcal{O}(\varepsilon^{-2})$ 次迭代。所提算法在多个数据集上进行了评估,结果表明 Midas-LL1 在计算速度和解的质量两方面均优于现有最先进算法。

英文摘要:

In this paper, we explore a specific optimization problem that combines a differentiable nonconvex function with a nondifferentiable function for multi-block variables, which is particularly relevant to tackle the multilinear rank-($L_r$,$L_r$,1) block-term tensor decomposition model with a regularization term. While existing algorithms often suffer from high per-iteration complexity and slow convergence, this paper employs a unified multi-step inertial accelerated doubly stochastic gradient descent method tailored for structured rank-$\left(L_r, L_r, 1\right)$ tensor decomposition, referred to as Midas-LL1. We also introduce an extended multi-step variance-reduced stochastic estimator framework. Our analysis under this new framework demonstrates the subsequential and sequential convergence of the proposed algorithm under certain conditions and illustrates the sublinear convergence rate of the subsequence, showing that the Midas-LL1 algorithm requires at most $\mathcal{O}(\varepsilon^{-2})$ iterations in expectation to reach an $\varepsilon$-stationary point. The proposed algorithm is evaluated on several datasets, and the results indicate that Midas-LL1 outperforms existing state-of-the-art algorithms in terms of both computational speed and solution quality.

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。

↑