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 2005.11807math.STstat.TH
收藏

算子范数损失下的最优奇异值收缩

Optimal singular value shrinkage for operator norm loss

William Leeb

摘要:

研究了低秩矩阵的奇异值收缩去噪问题。Gavish和Donoho最近的工作构建了一个框架,为广泛的一类损失函数寻找最佳奇异值收缩。我们使用这个框架来获得最佳收缩算子范数损失。最佳的收缩匹配的收缩提出的方阵的特殊情况下,由Gavish和Donoho,但不同的所有其他纵横比。我们精确地量化了使用最佳收缩器的准确性增益。我们还表明,最佳收缩收敛到最好的线性预测在经典的制度的纵横比为零。

英文摘要:

We study the denoising of low-rank matrices by singular value shrinkage. Recent work of Gavish and Donoho constructs a framework for finding optimal singular value shrinkers for a wide class of loss functions. We use this framework to derive the optimal shrinker for operator norm loss. The optimal shrinker matches the shrinker proposed by Gavish and Donoho in the special case of square matrices, but differs for all other aspect ratios. We precisely quantify the gain in accuracy from using the optimal shrinker. We also show that the optimal shrinker converges to the best linear predictor in the classical regime of aspect ratio zero.

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。

↑