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。
translated by 谷歌翻译
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} $中可能不良条件变得不可知。
translated by 谷歌翻译
我们考虑最大程度地减少两次不同的可差异,$ 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。
translated by 谷歌翻译
我们研究了张量张量的回归,其中的目标是将张量的响应与张量协变量与塔克等级参数张量/矩阵连接起来,而没有其内在等级的先验知识。我们提出了Riemannian梯度下降(RGD)和Riemannian Gauss-Newton(RGN)方法,并通过研究等级过度参数化的影响来应对未知等级的挑战。我们通过表明RGD和RGN分别线性地和四边形地收敛到两个等级的统计最佳估计值,从而为一般的张量调节回归提供了第一个收敛保证。我们的理论揭示了一种有趣的现象:Riemannian优化方法自然地适应了过度参数化,而无需修改其实施。我们还为低度多项式框架下的标量调整回归中的统计计算差距提供了第一个严格的证据。我们的理论证明了``统计计算差距的祝福''现象:在张张量的张量回归中,对于三个或更高的张紧器,在张张量的张量回归中,计算所需的样本量与中等级别相匹配的计算量相匹配。在考虑计算可行的估计器时,虽然矩阵设置没有此类好处。这表明中等等级的过度参数化本质上是``在张量调整的样本量三分或更高的样本大小上,三分或更高的样本量。最后,我们进行仿真研究以显示我们提出的方法的优势并证实我们的理论发现。
translated by 谷歌翻译
我们研究了神经网络中平方损耗训练问题的优化景观和稳定性,但通用非线性圆锥近似方案。据证明,如果认为非线性圆锥近似方案是(以适当定义的意义)比经典线性近似方法更具表现力,并且如果存在不完美的标签向量,则在方位损耗的训练问题必须在其中不稳定感知其解决方案集在训练数据中的标签向量上不连续地取决于标签向量。我们进一步证明对这些不稳定属性负责的效果也是马鞍点出现的原因和杂散的局部最小值,这可能是从全球解决方案的任意遥远的,并且既不训练问题也不是训练问题的不稳定性通常,杂散局部最小值的存在可以通过向目标函数添加正则化术语来克服衡量近似方案中参数大小的目标函数。无论可实现的可实现性是否满足,后一种结果都被证明是正确的。我们表明,我们的分析特别适用于具有可变宽度的自由结插值方案和深层和浅层神经网络的培训问题,其涉及各种激活功能的任意混合(例如,二进制,六骨,Tanh,arctan,软标志, ISRU,Soft-Clip,SQNL,Relu,Lifley Relu,Soft-Plus,Bent Identity,Silu,Isrlu和ELU)。总之,本文的发现说明了神经网络和一般非线性圆锥近似仪器的改进近似特性以直接和可量化的方式与必须解决的优化问题的不期望的性质链接,以便训练它们。
translated by 谷歌翻译
We study a general matrix optimization problem with a fixed-rank positive semidefinite (PSD) constraint. We perform the Burer-Monteiro factorization and consider a particular Riemannian quotient geometry in a search space that has a total space equipped with the Euclidean metric. When the original objective f satisfies standard restricted strong convexity and smoothness properties, we characterize the global landscape of the factorized objective under the Riemannian quotient geometry. We show the entire search space can be divided into three regions: (R1) the region near the target parameter of interest, where the factorized objective is geodesically strongly convex and smooth; (R2) the region containing neighborhoods of all strict saddle points; (R3) the remaining regions, where the factorized objective has a large gradient. To our best knowledge, this is the first global landscape analysis of the Burer-Monteiro factorized objective under the Riemannian quotient geometry. Our results provide a fully geometric explanation for the superior performance of vanilla gradient descent under the Burer-Monteiro factorization. When f satisfies a weaker restricted strict convexity property, we show there exists a neighborhood near local minimizers such that the factorized objective is geodesically convex. To prove our results we provide a comprehensive landscape analysis of a matrix factorization problem with a least squares objective, which serves as a critical bridge. Our conclusions are also based on a result of independent interest stating that the geodesic ball centered at Y with a radius 1/3 of the least singular value of Y is a geodesically convex set under the Riemannian quotient geometry, which as a corollary, also implies a quantitative bound of the convexity radius in the Bures-Wasserstein space. The convexity radius obtained is sharp up to constants.
translated by 谷歌翻译
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。
translated by 谷歌翻译
In this paper, we consider the geometric landscape connection of the widely studied manifold and factorization formulations in low-rank positive semidefinite (PSD) and general matrix optimization. We establish a sandwich relation on the spectrum of Riemannian and Euclidean Hessians at first-order stationary points (FOSPs). As a result of that, we obtain an equivalence on the set of FOSPs, second-order stationary points (SOSPs) and strict saddles between the manifold and the factorization formulations. In addition, we show the sandwich relation can be used to transfer more quantitative geometric properties from one formulation to another. Similarities and differences in the landscape connection under the PSD case and the general case are discussed. To the best of our knowledge, this is the first geometric landscape connection between the manifold and the factorization formulations for handling rank constraints, and it provides a geometric explanation for the similar empirical performance of factorization and manifold approaches in low-rank matrix optimization observed in the literature. In the general low-rank matrix optimization, the landscape connection of two factorization formulations (unregularized and regularized ones) is also provided. By applying these geometric landscape connections, in particular, the sandwich relation, we are able to solve unanswered questions in literature and establish stronger results in the applications on geometric analysis of phase retrieval, well-conditioned low-rank matrix optimization, and the role of regularization in factorization arising from machine learning and signal processing.
translated by 谷歌翻译
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.
translated by 谷歌翻译
最近以来,在理解与overparameterized模型非凸损失基于梯度的方法收敛性和泛化显著的理论进展。尽管如此,优化和推广,尤其是小的随机初始化的关键作用的许多方面都没有完全理解。在本文中,我们迈出玄机通过证明小的随机初始化这个角色的步骤,然后通过梯度下降的行为类似于流行谱方法的几个迭代。我们还表明,从小型随机初始化,这可证明是用于overparameterized车型更加突出这种隐含的光谱偏差,也使梯度下降迭代在一个特定的轨迹走向,不仅是全局最优的,但也很好期广义的解决方案。具体而言,我们专注于通过天然非凸制剂重构从几个测量值的低秩矩阵的问题。在该设置中,我们表明,从小的随机初始化的梯度下降迭代的轨迹可以近似分解为三个阶段:(Ⅰ)的光谱或对准阶段,其中,我们表明,该迭代具有一个隐含的光谱偏置类似于频谱初始化允许我们表明,在该阶段中进行迭代,并且下面的低秩矩阵的列空间被充分对准的端部,(II)一鞍回避/细化阶段,我们表明,该梯度的轨迹从迭代移动离开某些简并鞍点,和(III)的本地细化阶段,其中,我们表明,避免了鞍座后的迭代快速收敛到底层低秩矩阵。底层我们的分析是,可能有超出低等级的重建计算问题影响overparameterized非凸优化方案的分析见解。
translated by 谷歌翻译
在深度学习中的优化分析是连续的,专注于(变体)梯度流动,或离散,直接处理(变体)梯度下降。梯度流程可符合理论分析,但是风格化并忽略计算效率。它代表梯度下降的程度是深度学习理论的一个开放问题。目前的论文研究了这个问题。将梯度下降视为梯度流量初始值问题的近似数值问题,发现近似程度取决于梯度流动轨迹周围的曲率。然后,我们表明,在具有均匀激活的深度神经网络中,梯度流动轨迹享有有利的曲率,表明它们通过梯度下降近似地近似。该发现允许我们将深度线性神经网络的梯度流分析转换为保证梯度下降,其几乎肯定会在随机初始化下有效地收敛到全局最小值。实验表明,在简单的深度神经网络中,具有传统步长的梯度下降确实接近梯度流。我们假设梯度流动理论将解开深入学习背后的奥秘。
translated by 谷歌翻译
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.
translated by 谷歌翻译
We introduce a class of first-order methods for smooth constrained optimization that are based on an analogy to non-smooth dynamical systems. Two distinctive features of our approach are that (i) projections or optimizations over the entire feasible set are avoided, in stark contrast to projected gradient methods or the Frank-Wolfe method, and (ii) iterates are allowed to become infeasible, which differs from active set or feasible direction methods, where the descent motion stops as soon as a new constraint is encountered. The resulting algorithmic procedure is simple to implement even when constraints are nonlinear, and is suitable for large-scale constrained optimization problems in which the feasible set fails to have a simple structure. The key underlying idea is that constraints are expressed in terms of velocities instead of positions, which has the algorithmic consequence that optimizations over feasible sets at each iteration are replaced with optimizations over local, sparse convex approximations. In particular, this means that at each iteration only constraints that are violated are taken into account. The result is a simplified suite of algorithms and an expanded range of possible applications in machine learning.
translated by 谷歌翻译
在深度学习中,常见的是神经网络,即使用比训练样本更多的参数。非常令人惊讶地训练神经网络(随机)梯度下降导致概括得很好的模型,而古典统计会提出过度装备。为了了解这种隐含偏差现象,我们研究了自己感兴趣的稀疏恢复(压缩感测)的特殊情况。更确切地说,为了重建来自未确定的线性测量的矢量,我们引入了相应的过正常的方形损耗功能,其中要重建的载体深深地分解成几个载体。我们表明,在测量矩阵上的一个非常温和的假设下,用于过次分辨率的损耗功能的香草梯度流量会聚到最小$ \ ell_1 $ -norm的解决方案。后者众所周知,可以促进稀疏解决方案。作为副产品,我们的结果显着提高了先前作品中压缩感应的样本复杂性。该理论准确地预测数值实验中的回收率。对于证明,我们介绍了{\ texit {solution entopy}}的概念,它绕过了非凸起引起的障碍,并且应该是独立的兴趣。
translated by 谷歌翻译
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.
translated by 谷歌翻译
我们表明,在固定级和对称的阳性半明确矩阵上,Riemannian梯度下降算法几乎可以肯定地逃脱了歧管边界上的一些虚假关键点。我们的结果是第一个部分克服低级基质歧管的不完整而不改变香草riemannian梯度下降算法的不完整性。虚假的关键点是一些缺陷的矩阵,仅捕获地面真理的特征成分的一部分。与经典的严格鞍点不同,它们表现出非常奇异的行为。我们表明,使用动力学低级别近似和重新升级的梯度流,可以将某些伪造的临界点转换为参数化域中的经典严格鞍点,从而导致所需的结果。提供数值实验以支持我们的理论发现。
translated by 谷歌翻译
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。
translated by 谷歌翻译
在本文中,我们提出{\ it \下划线{r} ecursive} {\ it \ usef \ undesline {i} mortance} {\ it \ it \ usew supsline {s} ketching} algorithM squares {\ it \下划线{o} ptimization}(risro)。 Risro的关键步骤是递归重要性草图,这是一个基于确定性设计的递归投影的新素描框架,它与文献中的随机素描\ Citep {Mahoney2011 randomized,Woodruff2014sketching}有很大不同。在这个新的素描框架下,可以重新解释文献中的几种现有算法,而Risro比它们具有明显的优势。 Risro易于实现,并在计算上有效,其中每次迭代中的核心过程是解决降低尺寸最小二乘问题的问题。我们在某些轻度条件下建立了Risro的局部二次线性和二次收敛速率。我们还发现了Risro与Riemannian Gauss-Newton算法在固定等级矩阵上的联系。在机器学习和统计数据中的两种应用中,RISRO的有效性得到了证明:低级别矩阵痕量回归和相位检索。仿真研究证明了Risro的出色数值性能。
translated by 谷歌翻译
了解随机梯度下降(SGD)的隐式偏见是深度学习的关键挑战之一,尤其是对于过度透明的模型,损失功能的局部最小化$ l $可以形成多种多样的模型。从直觉上讲,SGD $ \ eta $的学习率很小,SGD跟踪梯度下降(GD),直到它接近这种歧管为止,梯度噪声阻止了进一步的收敛。在这样的政权中,Blanc等人。 (2020)证明,带有标签噪声的SGD局部降低了常规术语,损失的清晰度,$ \ mathrm {tr} [\ nabla^2 l] $。当前的论文通过调整Katzenberger(1991)的想法提供了一个总体框架。它原则上允许使用随机微分方程(SDE)描述参数的限制动力学的SGD围绕此歧管的正规化效应(即“隐式偏见”)的正则化效应,这是由损失共同确定的功能和噪声协方差。这产生了一些新的结果:(1)与Blanc等人的局部分析相比,对$ \ eta^{ - 2} $ steps有效的隐性偏差进行了全局分析。 (2020)仅适用于$ \ eta^{ - 1.6} $ steps和(2)允许任意噪声协方差。作为一个应用程序,我们以任意大的初始化显示,标签噪声SGD始终可以逃脱内核制度,并且仅需要$ o(\ kappa \ ln d)$样本用于学习$ \ kappa $ -sparse $ -sparse yroverparame parametrized linearized Linear Modal in $ \ Mathbb {r}^d $(Woodworth等,2020),而GD在内核制度中初始化的GD需要$ \ omega(d)$样本。该上限是最小值的最佳,并改善了先前的$ \ tilde {o}(\ kappa^2)$上限(Haochen等,2020)。
translated by 谷歌翻译
对于光滑的强凸目标,梯度下降的经典理论可确保相对于梯度评估的数量的线性收敛。一个类似的非球形理论是具有挑战性的:即使目标在每一次迭代的目标流畅时,相应的本地模型也是不稳定的,传统的补救措施需要不可预测的许多切割平面。我们提出了对局部优化的梯度下降迭代的多点概括。虽然设计了一般目标,但我们受到“最大平滑”模型的动机,可在最佳状态下捕获子样本维度。当目标本身自象最大的情况时,我们证明了线性融合,并且实验表明了更普遍的现象。
translated by 谷歌翻译