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 1802.06286cs.ITcs.LGmath.ITstat.ML
收藏

秩一测度的非凸矩阵分解

Nonconvex Matrix Factorization from Rank-One Measurements

Carnegie Mellon University(卡内基梅隆大学);Princeton University(普林斯顿大学)

Yuanxin Li, Cong Ma, Yuxin Chen, Yuejie Chi

摘要:

我们考虑从随机秩一测量中恢复低秩矩阵的问题,该问题跨越了许多应用,包括协方差绘制、相位恢复、量子态层析成像和学习浅多项式神经网络等。我们的方法是直接估计的低秩因子,通过香草梯度下降最小化非凸二次损失函数,定制的频谱初始化。当真秩较小时,该算法保证以接近最优的样本复杂度和计算复杂性收敛到地面真值(直到全局模糊度)。据我们所知,这是在两个指标中实现接近最优的第一个保证。特别地,接近最优计算保证的关键使能器是隐式正则化现象:在没有显式正则化的情况下,谱初始化和梯度下降迭代都自动地停留在与测量向量不相干的区域内。该特征允许采用与先前文献中建议的步长相比更积极的步长,而不需要样本分裂。

英文摘要:

We consider the problem of recovering low-rank matrices from random rank-one measurements, which spans numerous applications including covariance sketching, phase retrieval, quantum state tomography, and learning shallow polynomial neural networks, among others. Our approach is to directly estimate the low-rank factor by minimizing a nonconvex quadratic loss function via vanilla gradient descent, following a tailored spectral initialization. When the true rank is small, this algorithm is guaranteed to converge to the ground truth (up to global ambiguity) with near-optimal sample complexity and computational complexity. To the best of our knowledge, this is the first guarantee that achieves near-optimality in both metrics. In particular, the key enabler of near-optimal computational guarantees is an implicit regularization phenomenon: without explicit regularization, both spectral initialization and the gradient descent iterates automatically stay within a region incoherent with the measurement vectors. This feature allows one to employ much more aggressive step sizes compared with the ones suggested in prior literature, without the need of sample splitting.

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。

↑