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 1507.03032cs.LG
收藏

基于随机矩阵扰动的谱平滑

Spectral Smoothing via Random Matrix Perturbations

Jacob Abernethy, Chansoo Lee, Ambuj Tewari

摘要:

我们考虑随机光滑的谱函数的矩阵扰动通常研究随机矩阵理论。我们表明,频谱函数保持频谱平滑时,使用酉不变的扰动分布。然后,我们推导出国家的最先进的平滑边界的最大特征值函数使用高斯正交包络(GOE)。最大特征值函数的光滑化在半定优化和在线学习中具有重要的应用。作为我们的GOE平滑结果的直接后果,我们得到了一个$O((N \log N)^{1/4} \sqrt{T})$预期的遗憾界的在线方差最小化问题使用的算法,只执行一个最大特征向量计算每一个时间步。这里,$T$是轮数,$N$是矩阵维数。我们的算法和它的分析也扩展到更一般的在线PCA问题,学习者必须输出一个秩$k$子空间。该算法每步只需要计算$k$最大特征向量,并具有$O(k (N \log N)^{1/4} \sqrt{T})$期望遗憾界.

英文摘要:

We consider stochastic smoothing of spectral functions of matrices using perturbations commonly studied in random matrix theory. We show that a spectral function remains spectral when smoothed using a unitarily invariant perturbation distribution. We then derive state-of-the-art smoothing bounds for the maximum eigenvalue function using the Gaussian Orthogonal Ensemble (GOE). Smoothing the maximum eigenvalue function is important for applications in semidefinite optimization and online learning. As a direct consequence of our GOE smoothing results, we obtain an $O((N \log N)^{1/4} \sqrt{T})$ expected regret bound for the online variance minimization problem using an algorithm that performs only a single maximum eigenvector computation per time step. Here $T$ is the number of rounds and $N$ is the matrix dimension. Our algorithm and its analysis also extend to the more general online PCA problem where the learner has to output a rank $k$ subspace. The algorithm just requires computing $k$ maximum eigenvectors per step and enjoys an $O(k (N \log N)^{1/4} \sqrt{T})$ expected regret bound.

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。

↑