We provide stronger and more general primal-dual convergence results for Frank-Wolfe-type algorithms (a.k.a. conditional gradient) for constrained convex optimization, enabled by a simple framework of duality gap certificates. Our analysis also holds if the linear subproblems are only solved approximately (as well as if the gradients are inexact), and is proven to be worst-case optimal in the sparsity of the obtained solutions.On the application side, this allows us to unify a large variety of existing sparse greedy methods, in particular for optimization over convex hulls of an atomic set, even if those sets can only be approximated, including sparse (or structured sparse) vectors or matrices, low-rank matrices, permutation matrices, or max-norm bounded matrices. We present a new general framework for convex optimization over matrix factorizations, where every Frank-Wolfe iteration will consist of a low-rank update, and discuss the broad application areas of this approach.
translated by 谷歌翻译
本文提出了弗兰克 - 沃尔夫(FW)的新变种​​,称为$ k $ fw。标准FW遭受缓慢的收敛性:迭代通常是Zig-zag作为更新方向振荡约束集的极端点。新变种,$ k $ fw,通过在每次迭代中使用两个更强的子问题oracelles克服了这个问题。第一个是$ k $线性优化Oracle($ k $ loo),计算$ k $最新的更新方向(而不是一个)。第二个是$ k $方向搜索($ k $ ds),最大限度地减少由$ k $最新更新方向和之前迭代表示的约束组的目标。当问题解决方案承认稀疏表示时,奥克斯都易于计算,而且$ k $ FW会迅速收敛,以便平滑凸起目标和几个有趣的约束集:$ k $ fw实现有限$ \ frac {4l_f ^ 3d ^} { \ Gamma \ Delta ^ 2} $融合在多台和集团规范球上,以及光谱和核规范球上的线性收敛。数值实验验证了$ k $ fw的有效性,并展示了现有方法的数量级加速。
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
我们考虑凸优化问题,这些问题被广泛用作低级基质恢复问题的凸松弛。特别是,在几个重要问题(例如相位检索和鲁棒PCA)中,在许多情况下的基本假设是最佳解决方案是排名一列。在本文中,我们考虑了目标上的简单自然的条件,以使这些放松的最佳解决方案确实是独特的,并且是一个排名。主要是,我们表明,在这种情况下,使用线路搜索的标准Frank-Wolfe方法(即,没有任何参数调整),该方法仅需要单个排名一级的SVD计算,可以找到$ \ epsilon $ - 仅在$ o(\ log {1/\ epsilon})$迭代(而不是以前最著名的$ o(1/\ epsilon)$)中的近似解决方案,尽管目的不是强烈凸。我们考虑了基本方法的几种变体,具有改善的复杂性,以及由强大的PCA促进的扩展,最后是对非平滑问题的扩展。
translated by 谷歌翻译
近期在应用于培训深度神经网络和数据分析中的其他优化问题中的非凸优化的优化算法的兴趣增加,我们概述了最近对非凸优化优化算法的全球性能保证的理论结果。我们从古典参数开始,显示一般非凸面问题无法在合理的时间内有效地解决。然后,我们提供了一个问题列表,可以通过利用问题的结构来有效地找到全球最小化器,因为可能的问题。处理非凸性的另一种方法是放宽目标,从找到全局最小,以找到静止点或局部最小值。对于该设置,我们首先为确定性一阶方法的收敛速率提出了已知结果,然后是最佳随机和随机梯度方案的一般理论分析,以及随机第一阶方法的概述。之后,我们讨论了非常一般的非凸面问题,例如最小化$ \ alpha $ -weakly-are-convex功能和满足Polyak-lojasiewicz条件的功能,这仍然允许获得一阶的理论融合保证方法。然后,我们考虑更高阶和零序/衍生物的方法及其收敛速率,以获得非凸优化问题。
translated by 谷歌翻译
广义自我符合是许多重要学习问题的目标功能中存在的关键属性。我们建立了一个简单的Frank-Wolfe变体的收敛速率,该变体使用开环步数策略$ \ gamma_t = 2/(t+2)$,获得了$ \ Mathcal {o}(1/t)$收敛率对于这类功能,就原始差距和弗兰克 - 沃尔夫差距而言,$ t $是迭代计数。这避免了使用二阶信息或估计以前工作的局部平滑度参数的需求。我们还显示了各种常见病例的收敛速率的提高,例如,当所考虑的可行区域均匀地凸或多面体时。
translated by 谷歌翻译
In model selection problems for machine learning, the desire for a well-performing model with meaningful structure is typically expressed through a regularized optimization problem. In many scenarios, however, the meaningful structure is specified in some discrete space, leading to difficult nonconvex optimization problems. In this paper, we connect the model selection problem with structure-promoting regularizers to submodular function minimization with continuous and discrete arguments. In particular, we leverage the theory of submodular functions to identify a class of these problems that can be solved exactly and efficiently with an agnostic combination of discrete and continuous optimization routines. We show how simple continuous or discrete constraints can also be handled for certain problem classes and extend these ideas to a robust optimization framework. We also show how some problems outside of this class can be embedded within the class, further extending the class of problems our framework can accommodate. Finally, we numerically validate our theoretical results with several proof-of-concept examples with synthetic and real-world data, comparing against state-of-the-art algorithms.
translated by 谷歌翻译
低级和非平滑矩阵优化问题捕获了统计和机器学习中的许多基本任务。尽管近年来在开发\ textIt {平滑}低级优化问题的有效方法方面取得了重大进展,这些问题避免了保持高级矩阵和计算昂贵的高级SVD,但不平滑问题的进步的步伐缓慢。在本文中,我们考虑了针对此类问题的标准凸放松。主要是,我们证明,在\ textit {严格的互补性}条件下,在相对温和的假设下,非平滑目标可以写成最大的光滑功能,近似于两个流行的\ textit {mirriry-prox}方法的变体: \ textIt {外部方法}和带有\ textIt {矩阵启用梯度更新}的镜像 - prox,当用“温暖启动”初始化时,将速率$ o(1/t)$的最佳解决方案收集到最佳解决方案,同时仅需要两个\ textIt {low-rank} svds每迭代。此外,对于外部方法,我们还考虑了严格互补性的放松版本,该版本在所需的SVD等级与我们需要初始化该方法的球的半径之间取决于权衡。我们通过几个非平滑级矩阵恢复任务的经验实验来支持我们的理论结果,这既证明了严格的互补性假设的合理性,又证明了我们所提出的低级镜像 - 镜像变体的有效收敛。
translated by 谷歌翻译
We consider neural networks with a single hidden layer and non-decreasing positively homogeneous activation functions like the rectified linear units. By letting the number of hidden units grow unbounded and using classical non-Euclidean regularization tools on the output weights, they lead to a convex optimization problem and we provide a detailed theoretical analysis of their generalization performance, with a study of both the approximation and the estimation errors. We show in particular that they are adaptive to unknown underlying linear structures, such as the dependence on the projection of the input variables onto a low-dimensional subspace. Moreover, when using sparsity-inducing norms on the input weights, we show that high-dimensional non-linear variable selection may be achieved, without any strong assumption regarding the data and with a total number of variables potentially exponential in the number of observations. However, solving this convex optimization problem in infinite dimensions is only possible if the non-convex subproblem of addition of a new unit can be solved efficiently. We provide a simple geometric interpretation for our choice of activation functions and describe simple conditions for convex relaxations of the finite-dimensional non-convex subproblem to achieve the same generalization error bounds, even when constant-factor approximations cannot be found. We were not able to find strong enough convex relaxations to obtain provably polynomial-time algorithms and leave open the existence or non-existence of such tractable algorithms with non-exponential sample complexities.
translated by 谷歌翻译
在本文中,我们提出了近似的Frank-Wolfe(FW)算法,以在\ textit {线性最小化oracle}(LMO)一般不能有效地获得图形结构的支持集上解决凸的优化问题。我们首先证明了两个流行的近似假设(\ textIt {addive}和\ textit {乘法差距错误)},对于我们的问题而言无效,因为一般不存在便宜的间隙 - 差异lmo oracle。取而代之的是,提出了一个新的\ textit {近似双重最大化oracle}(dmo),该(DMO)近似于内部产品而不是间隙。当目标为$ l $ -smooth时,我们证明了使用$ \ delta $ -Approximate DMO的标准FW方法收敛为$ \ Mathcal {o}(l / \ delta t +(1- \ delta)(\ delta)(\ delta)一般而言放松约束集。此外,当目标为$ \ mu $ -sronglongly凸面并且该解决方案是唯一的,FW的变体收敛到$ \ Mathcal {o}(l^2 \ log log(t)/(\ mu \ mu \ delta^6 T^) 2))$具有相同的触电复杂性。我们的经验结果表明,即使这些改进的界限也是悲观的,在恢复具有图形结构稀疏性的现实世界图像方面,有了显着改善。
translated by 谷歌翻译
我们研究无限制的黎曼优化的免投影方法。特别是,我们提出了黎曼弗兰克 - 沃尔夫(RFW)方法。我们将RFW的非渐近收敛率分析为最佳(高音)凸起问题,以及非凸起目标的临界点。我们还提出了一种实用的设置,其中RFW可以获得线性收敛速度。作为一个具体的例子,我们将RFW专用于正定矩阵的歧管,并将其应用于两个任务:(i)计算矩阵几何平均值(riemannian质心); (ii)计算Bures-Wasserstein重心。这两个任务都涉及大量凸间间隔约束,为此,我们表明RFW要求的Riemannian“线性”Oracle承认了闭合形式的解决方案;该结果可能是独立的兴趣。我们进一步专门从事RFW到特殊正交组,并表明这里也可以以封闭形式解决riemannian“线性”甲骨文。在这里,我们描述了数据矩阵同步的应用程序(促使问题)。我们补充了我们的理论结果,并对RFW对最先进的riemananian优化方法进行了实证比较,并观察到RFW竞争性地对计算黎曼心质的任务进行竞争性。
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
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.
translated by 谷歌翻译
我们研究基于Krylov子空间的迭代方法,用于在任何Schatten $ p $ Norm中的低级别近似值。在这里,通过矩阵向量产品访问矩阵$ a $ $如此$ \ | a(i -zz^\ top)\ | _ {s_p} \ leq(1+ \ epsilon)\ min_ {u^\ top u = i_k} } $,其中$ \ | m \ | _ {s_p} $表示$ m $的单数值的$ \ ell_p $ norm。对于$ p = 2 $(frobenius norm)和$ p = \ infty $(频谱规范)的特殊情况,musco and Musco(Neurips 2015)获得了基于Krylov方法的算法,该方法使用$ \ tilde {o}(k)(k /\ sqrt {\ epsilon})$ matrix-vector产品,改进na \“ ive $ \ tilde {o}(k/\ epsilon)$依赖性,可以通过功率方法获得,其中$ \ tilde {o} $抑制均可抑制poly $(\ log(dk/\ epsilon))$。我们的主要结果是仅使用$ \ tilde {o}(kp^{1/6}/\ epsilon^{1/3} {1/3})$ matrix $ matrix的算法 - 矢量产品,并为所有$ p \ geq 1 $。为$ p = 2 $工作,我们的限制改进了先前的$ \ tilde {o}(k/\ epsilon^{1/2})$绑定到$ \ tilde {o}(k/\ epsilon^{1/3})$。由于schatten- $ p $和schatten-$ \ infty $ norms在$(1+ \ epsilon)$ pers $ p时相同\ geq(\ log d)/\ epsilon $,我们的界限恢复了Musco和Musco的结果,以$ p = \ infty $。此外,我们证明了矩阵矢量查询$ \ omega的下限(1/\ epsilon^ {1/3})$对于任何固定常数$ p \ geq 1 $,表明令人惊讶的$ \ tilde {\ theta}(1/\ epsilon^{ 1/3})$是常数〜$ k $的最佳复杂性。为了获得我们的结果,我们介绍了几种新技术,包括同时对多个Krylov子空间进行优化,以及针对分区操作员的不平等现象。我们在[1,2] $中以$ p \的限制使用了Araki-lieb-thirring Trace不平等,而对于$ p> 2 $,我们呼吁对安装分区操作员的规范压缩不平等。
translated by 谷歌翻译
我们提出了一种新的基于同型的条件梯度方法,用于解决大量简单圆锥约束的凸优化问题。该模板的实例自然出现在半决赛编程问题中,这是组合优化问题的凸松弛。我们的方法是一种双环算法,其中通过自我符合屏障处理圆锥约束,并且内环采用条件梯度算法来近似分析中心路径,而外圈则更新了对时间溶液上的精度。和同喻参数。当面对最先进的SDP求解器时,我们的理论迭代复杂性具有竞争力,具有廉价的无投影子例程的决定性优势。提供了初步数值实验,以说明该方法的实际性能。
translated by 谷歌翻译
我们在高维批处理设置中提出了统计上健壮和计算高效的线性学习方法,其中功能$ d $的数量可能超过样本量$ n $。在通用学习环境中,我们采用两种算法,具体取决于所考虑的损失函数是否为梯度lipschitz。然后,我们将我们的框架实例化,包括几种应用程序,包括香草稀疏,群 - 帕克斯和低升级矩阵恢复。对于每种应用,这导致了有效而强大的学习算法,这些算法在重尾分布和异常值的存在下达到了近乎最佳的估计率。对于香草$ S $ -SPARSITY,我们能够以重型尾巴和$ \ eta $ - 腐败的计算成本与非企业类似物相当的计算成本达到$ s \ log(d)/n $速率。我们通过开放源代码$ \ mathtt {python} $库提供了有效的算法实现文献中提出的最新方法。
translated by 谷歌翻译
在本文中,我们研究了一类二聚体优化问题,也称为简单的双重优化,在其中,我们将光滑的目标函数最小化,而不是另一个凸的约束优化问题的最佳解决方案集。已经开发了几种解决此类问题的迭代方法。 las,它们的收敛保证并不令人满意,因为它们要么渐近,要么渐近,要么是收敛速度缓慢且最佳的。为了解决这个问题,在本文中,我们介绍了Frank-Wolfe(FW)方法的概括,以解决考虑的问题。我们方法的主要思想是通过切割平面在局部近似低级问题的解决方案集,然后运行FW型更新以减少上层目标。当上层目标是凸面时,我们表明我们的方法需要$ {\ mathcal {o}}(\ max \ {1/\ epsilon_f,1/\ epsilon_g \})$迭代才能找到$ \ \ \ \ \ \ epsilon_f $ - 最佳目标目标和$ \ epsilon_g $ - 最佳目标目标。此外,当高级目标是非convex时,我们的方法需要$ {\ MATHCAL {o}}(\ max \ {1/\ epsilon_f^2,1/(\ epsilon_f \ epsilon_g})查找$(\ epsilon_f,\ epsilon_g)$ - 最佳解决方案。我们进一步证明了在“较低级别问题的老年人错误约束假设”下的更强的融合保证。据我们所知,我们的方法实现了所考虑的二聚体问题的最著名的迭代复杂性。我们还向数值实验提出了数值实验。与最先进的方法相比,展示了我们方法的出色性能。
translated by 谷歌翻译
In this book chapter, we briefly describe the main components that constitute the gradient descent method and its accelerated and stochastic variants. We aim at explaining these components from a mathematical point of view, including theoretical and practical aspects, but at an elementary level. We will focus on basic variants of the gradient descent method and then extend our view to recent variants, especially variance-reduced stochastic gradient schemes (SGD). Our approach relies on revealing the structures presented inside the problem and the assumptions imposed on the objective function. Our convergence analysis unifies several known results and relies on a general, but elementary recursive expression. We have illustrated this analysis on several common schemes.
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
由于机器学习,统计和科学的应用,多边缘最佳运输(MOT)引起了极大的兴趣。但是,在大多数应用中,MOT的成功受到缺乏有效算法的严重限制。实际上,MOT一般需要在边际K及其支撑大小n的数量中指数时间n。本文开发了一个关于“结构”在poly(n,k)时间中可溶解的一般理论。我们开发了一个统一的算法框架,用于通过表征不同算法所需的“结构”来解决poly(n,k)时间中的MOT,这是根据双重可行性甲骨文的简单变体所需的。该框架有几个好处。首先,它使我们能够证明当前是最流行的MOT算法的Sinkhorn算法比其他算法要在poly(n,k)时间中求解MOT所需的结构更严格。其次,我们的框架使得为给定的MOT问题开发poly(n,k)时间算法变得更加简单。特别是(大约)解决双重可行性Oracle是必要和足够的 - 这更适合标准算法技术。我们通过为三个通用类成本结构类别的poly(n,k)时间算法开发poly(n,k)时间算法来说明这种易用性:(1)图形结构; (2)设定优化结构; (3)低阶和稀疏结构。对于结构(1),我们恢复了Sindhorn具有poly(n,k)运行时的已知结果;此外,我们为计算精确且稀疏的解决方案提供了第一个poly(n,k)时间算法。对于结构(2) - (3),我们给出了第一个poly(n,k)时间算法,甚至用于近似计算。这三个结构一起涵盖了许多MOT的当前应用。
translated by 谷歌翻译