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 1902.01644math.OCcs.LG
收藏

关于迹范数球上光滑凸极小化的低秩投影-梯度法的收敛性及相关问题

On the Convergence of Projected-Gradient Methods with Low-Rank Projections for Smooth Convex Minimization over Trace-Norm Balls and Related Problems

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

Dan Garber

摘要:

单位迹范数球上的光滑凸最小化问题是机器学习、信号处理、统计等领域中的一个重要最优化问题,它是恢复低秩矩阵的基础。虽然凸优化的一阶方法具有最优的收敛速度,但在最坏的情况下,它们需要在每次迭代时计算满秩SVD,以便计算到迹范数球上的投影。然而,这些满秩SVD计算禁止将此类方法应用于大型问题。一个简单而自然的启发式,以减少计算成本是近似的投影只使用低秩SVD。这就提出了一个问题,如果,在什么条件下,这个简单的启发式确实可以导致可证明的收敛到最优解。本文证明了任何最优解都是欧氏空间的中心。球内投影梯度映射允许的秩至多是梯度向量的最大奇异值的重数。此外,球的半径与该梯度向量的谱间隙成比例。我们展示了这如何容易地暗示局部收敛(即,从“热启动”初始化)的标准一阶方法,仅使用低秩SVD计算。我们还量化了“过度参数化”的影响,即,在这个球的半径上使用更高秩的SVD计算,显示它可以随着适度的更大秩而显着增加。我们还将我们的结果扩展到具有迹范数正则化的优化和有界迹正半定矩阵上的优化。我们的理论研究得到了具体的经验证据的支持,这些证据证明了\textit{correct}在现实世界数据集上具有低秩投影的一阶方法的收敛性。

英文摘要:

Smooth convex minimization over the unit trace-norm ball is an important optimization problem in machine learning, signal processing, statistics and other fields, that underlies many tasks in which one wishes to recover a low-rank matrix given certain measurements. While first-order methods for convex optimization enjoy optimal convergence rates, they require in worst-case to compute a full-rank SVD on each iteration, in order to compute the projection onto the trace-norm ball. These full-rank SVD computations however prohibit the application of such methods to large problems. A simple and natural heuristic to reduce the computational cost is to approximate the projection using only a low-rank SVD. This raises the question if, and under what conditions, this simple heuristic can indeed result in provable convergence to the optimal solution. In this paper we show that any optimal solution is a center of a Euclid. ball inside-which the projected-gradient mapping admits rank that is at most the multiplicity of the largest singular value of the gradient vector. Moreover, the radius of the ball scales with the spectral gap of this gradient vector. We show how this readily implies the local convergence (i.e., from a "warm-start" initialization) of standard first-order methods, using only low-rank SVD computations. We also quantify the effect of "over-parameterization", i.e., using SVD computations with higher rank, on the radius of this ball, showing it can increase dramatically with moderately larger rank. We extend our results also to the setting of optimization with trace-norm regularization and optimization over bounded-trace positive semidefinite matrices. Our theoretical investigation is supported by concrete empirical evidence that demonstrates the \textit{correct} convergence of first-order methods with low-rank projections on real-world datasets.

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。

↑