The nonconvex formulation of matrix completion problem has received significant attention in recent years due to its affordable complexity compared to the convex formulation. Gradient descent (GD) is the simplest yet efficient baseline algorithm for solving nonconvex optimization problems. The success of GD has been witnessed in many different problems in both theory and practice when it is combined with random initialization. However, previous works on matrix completion require either careful initialization or regularizers to prove the convergence of GD. In this work, we study the rank-1 symmetric matrix completion and prove that GD converges to the ground truth when small random initialization is used. We show that in logarithmic amount of iterations, the trajectory enters the region where local convergence occurs. We provide an upper bound on the initialization size that is sufficient to guarantee the convergence and show that a larger initialization can be used as more samples are available. We observe that implicit regularization effect of GD plays a critical role in the analysis, and for the entire trajectory, it prevents each entry from becoming much larger than the others.
翻译:近年来,矩阵完成问题的非碳化物配方由于与卷轴配方相比具有负担得起的复杂性而引起人们的极大关注。渐渐下降(GD)是解决非碳化物优化问题的简单而有效的基线算法。当GD与随机初始化相结合时,在理论和实践的许多不同问题上都见证了GD的成功。然而,以前的矩阵完成工作需要仔细初始化或正规化,以证明GD的趋同。在这项工作中,我们研究了一级对称矩阵完成情况,并证明在使用小规模随机初始化时GD会与地面对齐。我们表明,在对数的迭代量中,轨迹进入了发生本地趋同的区域。我们提供了初始化规模的上限,足以保证趋同,并表明更大的初始化可以用作更多的样本。我们注意到,GD的隐含的正规化效应在分析中发挥着关键作用,对于整个轨迹而言,它使每个条目都无法变得比其他大得多。