许多基本的低级优化问题，例如矩阵完成，相位同步/检索，功率系统状态估计和鲁棒PCA，可以作为矩阵传感问题提出。求解基质传感的两种主要方法是基于半决赛编程（SDP）和Burer-Monteiro（B-M）分解的。 SDP方法患有高计算和空间复杂性，而B-M方法可能由于问题的非跨性别而返回伪造解决方案。这些方法成功的现有理论保证导致了类似的保守条件，这可能错误地表明这些方法具有可比性的性能。在本文中，我们阐明了这两种方法之间的一些主要差异。首先，我们提出一类结构化矩阵完成问题，而B-M方法则以压倒性的概率失败，而SDP方法正常工作。其次，我们确定了B-M方法工作和SDP方法失败的一类高度稀疏矩阵完成问题。第三，我们证明，尽管B-M方法与未知解决方案的等级无关，但SDP方法的成功与解决方案的等级相关，并随着等级的增加而提高。与现有的文献主要集中在SDP和B-M工作的矩阵传感实例上，本文为每种方法的独特优点提供了与替代方法的唯一优点。

我们考虑最大程度地减少两次不同的可差异，$ l $ -smooth和$ \ mu $ -stronglongly凸面目标$ \ phi $ phi $ a $ n \ times n $ n $阳性阳性半finite $ m \ succeq0 $，在假设是最小化的假设$ m^{\ star} $具有低等级$ r^{\ star} \ ll n $。遵循burer- monteiro方法，我们相反，在因子矩阵$ x $ size $ n \ times r $的因素矩阵$ x $上最小化nonconvex objection $ f（x）= \ phi（xx^{t}）$。这实际上将变量的数量从$ o（n^{2}）$减少到$ O（n）$的少量，并且免费实施正面的半弱点，但要付出原始问题的均匀性。在本文中，我们证明，如果搜索等级$ r \ ge r^{\ star} $被相对于真等级$ r^{\ star} $的常数因子过度参数化，则如$ r> \ in frac {1} {4}（l/\ mu-1）^{2} r^{\ star} $，尽管非概念性，但保证本地优化可以从任何初始点转换为全局最佳。这显着改善了先前的$ r \ ge n $的过度参数化阈值，如果允许$ \ phi $是非平滑和/或非额外凸的，众所周知，这将是尖锐的，但会增加变量的数量到$ o（n^{2}）$。相反，没有排名过度参数化，我们证明只有$ \ phi $几乎完美地条件，并且条件数量为$ l/\ mu <3 $，我们才能证明这种全局保证是可能的。因此，我们得出的结论是，少量的过度参数化可能会导致非凸室的理论保证得到很大的改善 - 蒙蒂罗分解。

The affine rank minimization problem consists of finding a matrix of minimum rank that satisfies a given system of linear equality constraints. Such problems have appeared in the literature of a diverse set of fields including system identification and control, Euclidean embedding, and collaborative filtering. Although specific instances can often be solved with specialized algorithms, the general affine rank minimization problem is NP-hard, because it contains vector cardinality minimization as a special case.In this paper, we show that if a certain restricted isometry property holds for the linear transformation defining the constraints, the minimum rank solution can be recovered by solving a convex optimization problem, namely the minimization of the nuclear norm over the given affine space. We present several random ensembles of equations where the restricted isometry property holds with overwhelming probability, provided the codimension of the subspace is Ω(r(m + n) log mn), where m, n are the dimensions of the matrix, and r is its rank.The techniques used in our analysis have strong parallels in the compressed sensing framework. We discuss how affine rank minimization generalizes this pre-existing concept and outline a dictionary relating concepts from cardinality minimization to those of rank minimization. We also discuss several algorithmic approaches to solving the norm minimization relaxations, and illustrate our results with numerical examples.

我们考虑使用梯度下降来最大程度地减少$ f（x）= \ phi（xx^{t}）$在$ n \ times r $因件矩阵$ x $上，其中$ \ phi是一种基础平稳凸成本函数定义了$ n \ times n $矩阵。虽然只能在合理的时间内发现只有二阶固定点$ x $，但如果$ x $的排名不足，则其排名不足证明其是全球最佳的。这种认证全球最优性的方式必然需要当前迭代$ x $的搜索等级$ r $，以相对于级别$ r^{\ star} $过度参数化。不幸的是，过度参数显着减慢了梯度下降的收敛性，从$ r = r = r = r^{\ star} $的线性速率到$ r> r> r> r> r^{\ star} $，即使$ \ phi $是$ \ phi $强烈凸。在本文中，我们提出了一项廉价的预处理，该预处理恢复了过度参数化的情况下梯度下降回到线性的收敛速率，同时也使在全局最小化器$ x^{\ star} $中可能不良条件变得不可知。

在这项工作的第一部分[32]中，我们引入了针对二次约束二次程序的凸抛物线松弛，以及依次惩罚的抛物线释放算法，以恢复近乎最佳的可行解决方案。在第二部分中，我们表明，从可行的解决方案或满足某些规律性条件的近乎可行的解决方案开始，顺序惩罚的抛物线弛豫算法的收敛到满足Karush-Kuhn-tucker优化条件的点。接下来，我们介绍了基准非凸口QCQP问题的数值实验以及系统识别问题的大规模实例，证明了所提出的方法的效率。

众所周知，许多网络系统，例如电网，大脑和舆论动态社交网络，都可以遵守保护法。这种现象的例子包括电网中的基尔乔夫法律和社交网络中的意见共识。网络系统中的保护定律可以建模为$ x = b^{*} y $的平衡方程，其中$ b^{*} $的稀疏模式捕获了网络的连接，$ y，x \在\ mathbb {r}^p $中分别是节点上“电势”和“注入流”的向量。节点电位$ y $会导致跨边缘的流量，并且在节点上注入的流量$ x $是网络动力学的无关紧要的。在几个实用的系统中，网络结构通常是未知的，需要从数据估算。为此，可以访问节点电位$ y $的样本，但只有节点注射$ x $的统计信息。在这个重要问题的激励下，我们研究了$ n $ y $ y $ y $ y $ y $ y $ y $ y $ b^{*} $稀疏结构的估计，假设节点注射$ x $遵循高斯分布，并带有已知的发行协方差$ \ sigma_x $。我们建议在高维度中为此问题的新$ \ ell_ {1} $ - 正则最大似然估计器，网络的大小$ p $大于样本量$ n $。我们表明，此优化问题是目标中的凸，并接受了独特的解决方案。在新的相互不一致的条件下，我们在三重$（n，p，d）$上建立了足够的条件，对于$ b^{*} $的精确稀疏恢复是可能的； $ d $是图的程度。我们还建立了在元素最大，Frobenius和运营商规范中回收$ b^{*} $的保证。最后，我们通过对拟议估计量对合成和现实世界数据的性能进行实验验证来补充这些理论结果。

我们提出了一种凸锥程序，可推断随机点产品图（RDPG）的潜在概率矩阵。优化问题最大化Bernoulli最大似然函数，增加核规范正则化术语。双重问题具有特别良好的形式，与众所周知的SemideFinite程序放松MaxCut问题有关。使用原始双功率条件，我们绑定了原始和双解决方案的条目和等级。此外，我们在轻微的技术假设下绑定了最佳目标值并证明了略微修改模型的概率估计的渐近一致性。我们对合成RDPG的实验不仅恢复了自然集群，而且还揭示了原始数据的下面的低维几何形状。我们还证明该方法在空手道俱乐部图表和合成美国参议图中恢复潜在结构，并且可以扩展到最多几百个节点的图表。

通过内插机器在信号处理和机器学习中的新兴作用的推动，这项工作考虑了过度参数化矩阵分子的计算方面。在这种情况下，优化景观可能包含虚假的固定点（SSP），其被证明是全级矩阵。这些SSP的存在意味着不可能希望任何全球担保过度参数化矩阵分解。例如，当在SSP上初始化时，梯度流将永远被删除。尽管如此，尽管有这些SSP，我们在这项工作中建立了相应的优势函数的梯度流到全局最小化器，只要其初始化是缺陷并且足够接近可行性问题的可行性集合。我们在数值上观察到，当随机初始化时，通过原始 - 双算法启发的提出梯度流的启发式离散化是成功的。我们的结果与当地的细化方法形成鲜明的对比，该方法需要初始化接近优化问题的最佳集合。更具体地，我们成功避免了SSPS设置的陷阱，因为梯度流始终仍然是缺陷，而不是因为附近没有SSP。后者是本地细化方法的情况。此外，广泛使用的限制性肌肉属性在我们的主要结果中没有作用。

我们研究了估计多元高斯分布中的精度矩阵的问题，其中所有部分相关性都是非负面的，也称为多变量完全阳性的顺序阳性（$ \ mathrm {mtp} _2 $）。近年来，这种模型得到了重大关注，主要是由于有趣的性质，例如，无论底层尺寸如何，最大似然估计值都存在于两个观察。我们将此问题作为加权$ \ ell_1 $ -norm正常化高斯的最大似然估计下$ \ mathrm {mtp} _2 $约束。在此方向上，我们提出了一种新颖的预计牛顿样算法，该算法包含精心设计的近似牛顿方向，这导致我们具有与一阶方法相同的计算和内存成本的算法。我们证明提出的预计牛顿样算法会聚到问题的最小值。从理论和实验中，我们进一步展示了我们使用加权$ \ ell_1 $ -norm的制剂的最小化器能够正确地恢复基础精密矩阵的支持，而无需在$ \ ell_1 $ -norm中存在不连贯状态方法。涉及合成和实世界数据的实验表明，我们所提出的算法从计算时间透视比最先进的方法显着更有效。最后，我们在金融时序数据中应用我们的方法，这些数据对于显示积极依赖性，在那里我们在学习金融网络上的模块间值方面观察到显着性能。

This paper shows that a perturbed form of gradient descent converges to a second-order stationary point in a number iterations which depends only poly-logarithmically on dimension (i.e., it is almost "dimension-free"). The convergence rate of this procedure matches the wellknown convergence rate of gradient descent to first-order stationary points, up to log factors. When all saddle points are non-degenerate, all second-order stationary points are local minima, and our result thus shows that perturbed gradient descent can escape saddle points almost for free.Our results can be directly applied to many machine learning applications, including deep learning. As a particular concrete example of such an application, we show that our results can be used directly to establish sharp global convergence rates for matrix factorization. Our results rely on a novel characterization of the geometry around saddle points, which may be of independent interest to the non-convex optimization community.

组同步是指从嘈杂的成对测量中估计组元素的集合。这种非核解问题来自包括计算机视觉，机器人和冷冻电子显微镜的许多科学领域的大量关注。在本文中，我们专注于在不完全测量下的一般添加剂噪声模型的正交组同步问题，这比通常考虑的完整测量设置更多。从最优条件的透视提供正交组同步问题的特征以及投影梯度上升方法的固定点，其也称为广义功率方法（GPM）。值得注意的是，即使没有生成模型，这些结果仍然存在。同时，我们导出了对正交组同步问题的本地错误绑定属性，这对于不同算法的融合速率分析非常有用，并且可以是独立的兴趣。最后，我们在基于已建立的本地误差绑定属性的一般添加剂噪声模型下将GPM的线性收敛结果证明了GPM到全局最大化器。我们的理论会聚结果在若干确定性条件下持有，其可以覆盖具有对抗性噪声的某些情况，并且作为我们专门化以确定ERD \“OS-R”enyi测量图和高斯噪声的示例。

诸如压缩感测，图像恢复，矩阵/张恢复和非负矩阵分子等信号处理和机器学习中的许多近期问题可以作为约束优化。预计的梯度下降是一种解决如此约束优化问题的简单且有效的方法。本地收敛分析将我们对解决方案附近的渐近行为的理解，与全球收敛分析相比，收敛率的较小界限提供了较小的界限。然而，本地保证通常出现在机器学习和信号处理的特定问题领域。此稿件在约束最小二乘范围内，对投影梯度下降的局部收敛性分析提供了统一的框架。该建议的分析提供了枢转局部收敛性的见解，例如线性收敛的条件，收敛区域，精确的渐近收敛速率，以及达到一定程度的准确度所需的迭代次数的界限。为了证明所提出的方法的适用性，我们介绍了PGD的收敛分析的配方，并通过在四个基本问题上的配方的开始延迟应用来证明它，即线性约束最小二乘，稀疏恢复，最小二乘法使用单位规范约束和矩阵完成。

Autoencoders are a popular model in many branches of machine learning and lossy data compression. However, their fundamental limits, the performance of gradient methods and the features learnt during optimization remain poorly understood, even in the two-layer setting. In fact, earlier work has considered either linear autoencoders or specific training regimes (leading to vanishing or diverging compression rates). Our paper addresses this gap by focusing on non-linear two-layer autoencoders trained in the challenging proportional regime in which the input dimension scales linearly with the size of the representation. Our results characterize the minimizers of the population risk, and show that such minimizers are achieved by gradient methods; their structure is also unveiled, thus leading to a concise description of the features obtained via training. For the special case of a sign activation function, our analysis establishes the fundamental limits for the lossy compression of Gaussian sources via (shallow) autoencoders. Finally, while the results are proved for Gaussian data, numerical simulations on standard datasets display the universality of the theoretical predictions.

我们考虑指标变量和指标上的任意约束的凸二次优化问题。我们表明，在扩展空间中设置的凸壳描述，其具有二次数量的附加变量包括单个正半纤维限制（明确规定）和线性约束。特别地，对这类问题的凸起减少了描述在扩展制剂中的多面体集。我们还在变量的原始空间中说明：我们提供了基于无限数量的圆锥二次不等式的描述，这些锥形二次不等式是“有限地产生的”。特别地，可以表征给定的不等式是否需要描述凸船。这里介绍了新的理论统一了若干以前建立的结果，并铺平了利用多面体方法来分析混合整数非线性集的凸壳。

We investigate the problem of recovering a partially observed high-rank matrix whose columns obey a nonlinear structure such as a union of subspaces, an algebraic variety or grouped in clusters. The recovery problem is formulated as the rank minimization of a nonlinear feature map applied to the original matrix, which is then further approximated by a constrained non-convex optimization problem involving the Grassmann manifold. We propose two sets of algorithms, one arising from Riemannian optimization and the other as an alternating minimization scheme, both of which include first- and second-order variants. Both sets of algorithms have theoretical guarantees. In particular, for the alternating minimization, we establish global convergence and worst-case complexity bounds. Additionally, using the Kurdyka-Lojasiewicz property, we show that the alternating minimization converges to a unique limit point. We provide extensive numerical results for the recovery of union of subspaces and clustering under entry sampling and dense Gaussian sampling. Our methods are competitive with existing approaches and, in particular, high accuracy is achieved in the recovery using Riemannian second-order methods.

We consider a problem of considerable practical interest: the recovery of a data matrix from a sampling of its entries. Suppose that we observe m entries selected uniformly at random from a matrix M . Can we complete the matrix and recover the entries that we have not seen?We show that one can perfectly recover most low-rank matrices from what appears to be an incomplete set of entries. We prove that if the number m of sampled entries obeys m ≥ C n 1.2 r log n for some positive numerical constant C, then with very high probability, most n × n matrices of rank r can be perfectly recovered by solving a simple convex optimization program. This program finds the matrix with minimum nuclear norm that fits the data. The condition above assumes that the rank is not too large. However, if one replaces the 1.2 exponent with 1.25, then the result holds for all values of the rank. Similar results hold for arbitrary rectangular matrices as well. Our results are connected with the recent literature on compressed sensing, and show that objects other than signals and images can be perfectly reconstructed from very limited information.

本文涉及低级矩阵恢复问题的$ \ ell_ {2,0} $ \ ell_ {2,0} $ - 正则化分解模型及其计算。引入了Qual $ \ ell_ {2,0} $ - 因子矩阵的规范，以促进因素和低级别解决方案的柱稀疏性。对于这种不透露的不连续优化问题，我们开发了一种具有外推的交替的多种化 - 最小化（AMM）方法，以及一个混合AMM，其中提出了一种主要的交替的近端方法，以寻找与较少的非零列和带外推的AMM的初始因子对。然后用于最小化平滑的非凸损失。我们为所提出的AMM方法提供全局收敛性分析，并使用非均匀采样方案将它们应用于矩阵完成问题。数值实验是用综合性和实际数据示例进行的，并且与核形态正则化分解模型的比较结果和MAX-NORM正则化凸模型显示柱$ \ ell_ {2,0} $ - 正则化分解模型具有优势在更短的时间内提供较低误差和排名的解决方案。

Efforts to understand the generalization mystery in deep learning have led to the belief that gradient-based optimization induces a form of implicit regularization, a bias towards models of low "complexity." We study the implicit regularization of gradient descent over deep linear neural networks for matrix completion and sensing, a model referred to as deep matrix factorization. Our first finding, supported by theory and experiments, is that adding depth to a matrix factorization enhances an implicit tendency towards low-rank solutions, oftentimes leading to more accurate recovery. Secondly, we present theoretical and empirical arguments questioning a nascent view by which implicit regularization in matrix factorization can be captured using simple mathematical norms. Our results point to the possibility that the language of standard regularizers may not be rich enough to fully encompass the implicit regularization brought forth by gradient-based optimization.

We consider the nonlinear inverse problem of learning a transition operator $\mathbf{A}$ from partial observations at different times, in particular from sparse observations of entries of its powers $\mathbf{A},\mathbf{A}^2,\cdots,\mathbf{A}^{T}$. This Spatio-Temporal Transition Operator Recovery problem is motivated by the recent interest in learning time-varying graph signals that are driven by graph operators depending on the underlying graph topology. We address the nonlinearity of the problem by embedding it into a higher-dimensional space of suitable block-Hankel matrices, where it becomes a low-rank matrix completion problem, even if $\mathbf{A}$ is of full rank. For both a uniform and an adaptive random space-time sampling model, we quantify the recoverability of the transition operator via suitable measures of incoherence of these block-Hankel embedding matrices. For graph transition operators these measures of incoherence depend on the interplay between the dynamics and the graph topology. We develop a suitable non-convex iterative reweighted least squares (IRLS) algorithm, establish its quadratic local convergence, and show that, in optimal scenarios, no more than $\mathcal{O}(rn \log(nT))$ space-time samples are sufficient to ensure accurate recovery of a rank-$r$ operator $\mathbf{A}$ of size $n \times n$. This establishes that spatial samples can be substituted by a comparable number of space-time samples. We provide an efficient implementation of the proposed IRLS algorithm with space complexity of order $O(r n T)$ and per-iteration time complexity linear in $n$. Numerical experiments for transition operators based on several graph models confirm that the theoretical findings accurately track empirical phase transitions, and illustrate the applicability and scalability of the proposed algorithm.

找到给定矩阵的独特低维分解的问题是许多领域的基本和经常发生的问题。在本文中，我们研究了寻求一个唯一分解的问题，以\ mathbb {r} ^ {p \ times n} $ in \ mathbb {p \ time n} $。具体来说，我们考虑$ y = ax \ in \ mathbb {r} ^ {p \ time n} $，其中矩阵$ a \ in \ mathbb {r} ^ {p \ times r} $具有全列等级，带有$ r <\ min \ {n，p \} $，矩阵$ x \ in \ mathbb {r} ^ {r \ times n} $是元素 - 方向稀疏。我们证明，可以唯一确定$ y $的稀疏分解，直至某些内在签名排列。我们的方法依赖于解决在单位球体上限制的非凸优化问题。我们对非透露优化景观的几何分析表明，任何{\ em strict}本地解决方案靠近地面真相解决方案，可以通过任何二阶序列算法遵循的简单数据驱动初始化恢复。最后，我们用数值实验证实了这些理论结果。