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 1809.10491cs.LGmath.OCstat.ML
收藏

在线PCA非凸在线梯度上升的遗憾最小化

On the Regret Minimization of Nonconvex Online Gradient Ascent for Online PCA

Technion - Israel Institute of Technology(以色列理工学院)

Dan Garber

摘要:

在本文中,我们专注于问题的在线主成分分析的后悔最小化框架。对于这个问题,所有现有的后悔最小化算法的完全对抗设置是基于一个半正定凸松弛,因此需要二次记忆和SVD计算(薄或全)的每一个迭代,这相当于至少二次运行时间每次迭代。这与相应的随机i.i.d.的问题,这是最近被广泛研究的变种,并承认非常有效的梯度上升算法,直接对自然的非凸制定的问题,因此只需要线性内存和线性运行时间每次迭代。这就提出了一个问题:非凸在线梯度上升算法是否可以在在线对抗环境中最大限度地减少遗憾?在本文中,我们采取了一个步骤来回答这个问题。我们引入了一个\textit{adversarially-perturbed spiked-covariance model},其中每个数据点被假设为遵循一个固定的随机分布,在协方差矩阵中具有非零的谱间隙,但随后被一些对抗向量扰动。该模型是一个经过充分研究的标准随机设置的自然扩展,允许在数据中出现非平稳(对抗)模式,因此可能会更好地近似真实世界的数据流。我们表明,在一个有趣的制度的参数,当非凸的在线梯度上升算法初始化的“热启动”向量,它可证明最大限度地减少遗憾的概率很高。我们进一步讨论了计算这样一个“热启动”向量的可能性,以及使用正则化来获得快速的后悔率。我们的理论研究结果得到了合成和真实世界数据的实证实验的支持。

英文摘要:

In this paper we focus on the problem of Online Principal Component Analysis in the regret minimization framework. For this problem, all existing regret minimization algorithms for the fully-adversarial setting are based on a positive semidefinite convex relaxation, and hence require quadratic memory and SVD computation (either thin of full) on each iteration, which amounts to at least quadratic runtime per iteration. This is in stark contrast to a corresponding stochastic i.i.d. variant of the problem, which was studied extensively lately, and admits very efficient gradient ascent algorithms that work directly on the natural non-convex formulation of the problem, and hence require only linear memory and linear runtime per iteration. This raises the question: can non-convex online gradient ascent algorithms be shown to minimize regret in online adversarial settings? In this paper we take a step forward towards answering this question. We introduce an \textit{adversarially-perturbed spiked-covariance model} in which, each data point is assumed to follow a fixed stochastic distribution with a non-zero spectral gap in the covariance matrix, but is then perturbed with some adversarial vector. This model is a natural extension of a well studied standard stochastic setting that allows for non-stationary (adversarial) patterns to arise in the data and hence, might serve as a significantly better approximation for real-world data-streams. We show that in an interesting regime of parameters, when the non-convex online gradient ascent algorithm is initialized with a "warm-start" vector, it provably minimizes the regret with high probability. We further discuss the possibility of computing such a "warm-start" vector, and also the use of regularization to obtain fast regret rates. Our theoretical findings are supported by empirical experiments on both synthetic and real-world data.

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。

↑