几十年前,近端点算法(PPA)规定为抽象操作员理论和数值优化社区获得持久的吸引力。即使在现代应用中,研究人员仍然使用近端最小化理论来设计克服非现状的可扩展算法。卓越的作品作为\ Cite {FER:91,BER:82Constrom,BER:89,汤姆:11}在PPA的收敛行为与客观函数的规律之间建立了紧张关系。在本手稿中,我们得出了精确和不精确的PPA的非因素迭代复杂性,以最小化$ \ gamma-$持有人的增长:$ \ bigo {\ log(1 / \ epsilon)} $(在[1中, 2] $)和$ \ bigo {1 / \ epsilon ^ {\ gamma - 2}} $(适用于$ \ gamma> 2 $)。特别是,即使在不精确的情况下,我们恢复了PPA的众所周知的结果:有限的收敛性,用于急剧增长,即使是在不精确的情况下的二次生长。但是,在不考虑到计算每个PPA迭代的具体计算工作,任何迭代复杂性都仍然摘要和纯粹的信息。因此,使用计算不精确PPA迭代的内部(近端)梯度/子射频方法子程序,其次地显示了在重启的不精确PPA上的新颖的计算复杂性界限,当没有已知有关于目标函数的增长的信息时可用。在数值实验中,我们确认了我们框架的实际表现和可实现性。
translated by 谷歌翻译
近期在应用于培训深度神经网络和数据分析中的其他优化问题中的非凸优化的优化算法的兴趣增加,我们概述了最近对非凸优化优化算法的全球性能保证的理论结果。我们从古典参数开始,显示一般非凸面问题无法在合理的时间内有效地解决。然后,我们提供了一个问题列表,可以通过利用问题的结构来有效地找到全球最小化器,因为可能的问题。处理非凸性的另一种方法是放宽目标,从找到全局最小,以找到静止点或局部最小值。对于该设置,我们首先为确定性一阶方法的收敛速率提出了已知结果,然后是最佳随机和随机梯度方案的一般理论分析,以及随机第一阶方法的概述。之后,我们讨论了非常一般的非凸面问题,例如最小化$ \ 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
Convex function constrained optimization has received growing research interests lately. For a special convex problem which has strongly convex function constraints, we develop a new accelerated primal-dual first-order method that obtains an $\Ocal(1/\sqrt{\vep})$ complexity bound, improving the $\Ocal(1/{\vep})$ result for the state-of-the-art first-order methods. The key ingredient to our development is some novel techniques to progressively estimate the strong convexity of the Lagrangian function, which enables adaptive step-size selection and faster convergence performance. In addition, we show that the complexity is further improvable in terms of the dependence on some problem parameter, via a restart scheme that calls the accelerated method repeatedly. As an application, we consider sparsity-inducing constrained optimization which has a separable convex objective and a strongly convex loss constraint. In addition to achieving fast convergence, we show that the restarted method can effectively identify the sparsity pattern (active-set) of the optimal solution in finite steps. To the best of our knowledge, this is the first active-set identification result for sparsity-inducing constrained optimization.
translated by 谷歌翻译
我们分析了牛顿方法的变体的性能,并通过二次正则化来解决复合凸最小化问题。在我们方法的每个步骤中,我们选择正规化参数与当前点的梯度标准的某些功率成正比。我们介绍了一个以h \ h \“第二或第三个衍生物的较旧连续性为特征的问题类别。然后,我们使用简单的自适应搜索步骤介绍该方法,允许自动调整问题类,并以最佳的全球复杂性界限,而无需知道问题的特定参数。特别是,对于Lipschitz连续第三个导数的函数类别,我们获得了全局$ o(1/k^3)$ rate,以前归因于三阶张量方法。功能是均匀凸的,我们证明我们方案的自动加速度是合理的,导致全局速率和局部超线性收敛。不同的速率(sublinear,linear和superlinear)之间的切换是自动的。同样,没有先验的先验需要了解参数。
translated by 谷歌翻译
在本文中,我们开发了使用局部Lipschitz连续梯度(LLCG)的凸优化的一阶方法,该方法超出了lipschitz连续梯度的精心研究类别的凸优化。特别是,我们首先考虑使用LLCG进行无约束的凸优化,并提出求解它的加速近端梯度(APG)方法。所提出的APG方法配备了可验证的终止标准,并享受$ {\ cal o}的操作复杂性(\ varepsilon^{ - 1/2} \ log \ log \ varepsilon^{ - 1})$和$ {\ cal o {\ cal o }(\ log \ varepsilon^{ - 1})$用于查找不受约束的凸的$ \ varepsilon $ - 剩余凸和强烈凸优化问题的解决方案。然后,我们考虑使用LLCG进行约束的凸优化,并提出了一种近端增强拉格朗日方法,通过应用我们提出的APG方法之一来求解一系列近端增强拉格朗日子问题,以解决它。所得的方法配备了可验证的终止标准,并享受$ {\ cal o}的操作复杂性(\ varepsilon^{ - 1} \ log \ log \ varepsilon^{ - 1})$和$ {\ cal o}(\ cal o}(\ Varepsilon^{ - 1/2} \ log \ varepsilon^{ - 1})$用于查找约束凸的$ \ varepsilon $ -KKT解决方案,分别是强烈的凸优化问题。本文中所有提出的方法均无参数或几乎不含参数,但需要有关凸电参数的知识。据我们所知,没有进行先前的研究来研究具有复杂性保证的加速一阶方法,可与LLCG进行凸优化。本文获得的所有复杂性结果都是全新的。
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
非滑动优化在许多工程领域中找到了广泛的应用程序。在这项工作中,我们建议利用{随机坐标亚级别方法}(RCS)来求解非平滑凸凸和非平滑凸(非平滑弱弱凸)优化问题。在每次迭代中,RCS随机选择一个块坐标,而不是所有要更新的坐标。由实用应用激发,我们考虑了目标函数的{线性界限亚级别假设},这比Lipschitz的连续性假设要笼统得多。在这样的一般假设下,我们在凸和非凸病例中对RCS进行了彻底的收敛分析,并建立了预期的收敛速率和几乎确定的渐近收敛结果。为了得出这些收敛结果,我们建立了收敛的引理以及弱凸功能的全局度量超值属性与其莫罗膜的关系,它们是基本的和独立的利益。最后,我们进行了几项实验,以显示RC的优势比亚级别方法的优势。
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)$)中的近似解决方案,尽管目的不是强烈凸。我们考虑了基本方法的几种变体,具有改善的复杂性,以及由强大的PCA促进的扩展,最后是对非平滑问题的扩展。
translated by 谷歌翻译
最近有利息线性编程(LP)的一阶方法。在本文中,我们提出了一种使用差异减少的随机算法,并重新启动,用于解决LP等尖锐的原始 - 双重问题。我们表明,所提出的随机方法表现出具有高概率的尖锐实例的线性收敛速率,这提高了现有的确定性和随机算法的复杂性。此外,我们提出了一个有效的基于坐标的随机甲骨文,用于无限制的双线性问题,它具有$ \ Mathcal O(1)$彼得迭代成本并改善总牌数量达到一定的准确性。
translated by 谷歌翻译
Iterative regularization is a classic idea in regularization theory, that has recently become popular in machine learning. On the one hand, it allows to design efficient algorithms controlling at the same time numerical and statistical accuracy. On the other hand it allows to shed light on the learning curves observed while training neural networks. In this paper, we focus on iterative regularization in the context of classification. After contrasting this setting with that of regression and inverse problems, we develop an iterative regularization approach based on the use of the hinge loss function. More precisely we consider a diagonal approach for a family of algorithms for which we prove convergence as well as rates of convergence. Our approach compares favorably with other alternatives, as confirmed also in numerical simulations.
translated by 谷歌翻译
我们研究了具有有限和结构的平滑非凸化优化问题的随机重新洗脱(RR)方法。虽然该方法在诸如神经网络的训练之类的实践中广泛利用,但其会聚行为仅在几个有限的环境中被理解。在本文中,在众所周知的Kurdyka-LojasiewiCz(KL)不等式下,我们建立了具有适当递减步长尺寸的RR的强极限点收敛结果,即,RR产生的整个迭代序列是会聚并会聚到单个静止点几乎肯定的感觉。 In addition, we derive the corresponding rate of convergence, depending on the KL exponent and the suitably selected diminishing step sizes.当KL指数在$ [0,\ FRAC12] $以$ [0,\ FRAC12] $时,收敛率以$ \ mathcal {o}(t ^ { - 1})$的速率计算,以$ t $ counting迭代号。当KL指数属于$(\ FRAC12,1)$时,我们的派生收敛速率是FORM $ \ MATHCAL {O}(T ^ { - Q})$,$ Q \ IN(0,1)$取决于在KL指数上。基于标准的KL不等式的收敛分析框架仅适用于具有某种阶段性的算法。我们对基于KL不等式的步长尺寸减少的非下降RR方法进行了新的收敛性分析,这概括了标准KL框架。我们总结了我们在非正式分析框架中的主要步骤和核心思想,这些框架是独立的兴趣。作为本框架的直接应用,我们还建立了类似的强极限点收敛结果,为重组的近端点法。
translated by 谷歌翻译
在许多机器学习应用程序中出现了非convex-concave min-max问题,包括最大程度地减少一组非凸函数的最大程度,并对神经网络的强大对抗训练。解决此问题的一种流行方法是梯度下降(GDA)算法,不幸的是,在非凸性的情况下可以表现出振荡。在本文中,我们引入了一种“平滑”方案,该方案可以与GDA结合以稳定振荡并确保收敛到固定溶液。我们证明,稳定的GDA算法可以实现$ O(1/\ epsilon^2)$迭代复杂性,以最大程度地减少有限的非convex函数收集的最大值。此外,平滑的GDA算法达到了$ O(1/\ epsilon^4)$ toseration复杂性,用于一般的nonconvex-concave问题。提出了这种稳定的GDA算法的扩展到多块情况。据我们所知,这是第一个实现$ o(1/\ epsilon^2)$的算法,用于一类NonConvex-Concave问题。我们说明了稳定的GDA算法在健壮训练中的实际效率。
translated by 谷歌翻译
加速的近端算法(APPA),也称为“催化剂”,是从凸优化到近似近端计算(即正则最小化)的确定还原。这种减少在概念上是优雅的,可以保证强大的收敛速度。但是,这些速率具有多余的对数项,因此需要计算每个近端点至高精度。在这项工作中,我们提出了一个新颖的放松误差标准,用于加速近端点(recapp),以消除对高精度子问题解决方案的需求。我们将recapp应用于两个规范问题:有限的和最大结构的最小化。对于有限和问题,我们匹配了以前通过精心设计的问题特异性算法获得的最著名的复杂性。为了最大程度地减少$ \ max_y f(x,y)$,其中$ f $以$ x $为$ x $,而在$ y $中强烈concave,我们改进了受对数因素限制的最著名的(基于催化剂)。
translated by 谷歌翻译
现代统计应用常常涉及最小化可能是非流动和/或非凸起的目标函数。本文侧重于广泛的Bregman-替代算法框架,包括本地线性近似,镜像下降,迭代阈值,DC编程以及许多其他实例。通过广义BREGMAN功能的重新发出使我们能够构建合适的误差测量并在可能高维度下建立非凸起和非凸起和非球形目标的全球收敛速率。对于稀疏的学习问题,在一些规律性条件下,所获得的估算器作为代理人的固定点,尽管不一定是局部最小化者,但享受可明确的统计保障,并且可以证明迭代顺序在所需的情况下接近统计事实准确地快速。本文还研究了如何通过仔细控制步骤和放松参数来设计基于适应性的动力的加速度而不假设凸性或平滑度。
translated by 谷歌翻译
在本文中,我们介绍了泰坦(Titan),这是一种新型的惯性块最小化框架,用于非平滑非凸优化问题。据我们所知,泰坦是块坐标更新方法的第一个框架,该方法依赖于大型最小化框架,同时将惯性力嵌入到块更新的每个步骤中。惯性力是通过外推算子获得的,该操作员累积了重力和Nesterov型加速度,以作为特殊情况作为块近端梯度方法。通过选择各种替代功能,例如近端,Lipschitz梯度,布雷格曼,二次和复合替代功能,并通过改变外推操作员来生成一组丰富的惯性块坐标坐标更新方法。我们研究了泰坦生成序列的子顺序收敛以及全局收敛。我们说明了泰坦对两个重要的机器学习问题的有效性,即稀疏的非负矩阵分解和矩阵完成。
translated by 谷歌翻译
We consider minimizing a smooth and strongly convex objective function using a stochastic Newton method. At each iteration, the algorithm is given an oracle access to a stochastic estimate of the Hessian matrix. The oracle model includes popular algorithms such as Subsampled Newton and Newton Sketch. Despite using second-order information, these existing methods do not exhibit superlinear convergence, unless the stochastic noise is gradually reduced to zero during the iteration, which would lead to a computational blow-up in the per-iteration cost. We propose to address this limitation with Hessian averaging: instead of using the most recent Hessian estimate, our algorithm maintains an average of all the past estimates. This reduces the stochastic noise while avoiding the computational blow-up. We show that this scheme exhibits local $Q$-superlinear convergence with a non-asymptotic rate of $(\Upsilon\sqrt{\log (t)/t}\,)^{t}$, where $\Upsilon$ is proportional to the level of stochastic noise in the Hessian oracle. A potential drawback of this (uniform averaging) approach is that the averaged estimates contain Hessian information from the global phase of the method, i.e., before the iterates converge to a local neighborhood. This leads to a distortion that may substantially delay the superlinear convergence until long after the local neighborhood is reached. To address this drawback, we study a number of weighted averaging schemes that assign larger weights to recent Hessians, so that the superlinear convergence arises sooner, albeit with a slightly slower rate. Remarkably, we show that there exists a universal weighted averaging scheme that transitions to local convergence at an optimal stage, and still exhibits a superlinear convergence rate nearly (up to a logarithmic factor) matching that of uniform Hessian averaging.
translated by 谷歌翻译
Theoretical properties of bilevel problems are well studied when the lower-level problem is strongly convex. In this work, we focus on bilevel optimization problems without the strong-convexity assumption. In these cases, we first show that the common local optimality measures such as KKT condition or regularization can lead to undesired consequences. Then, we aim to identify the mildest conditions that make bilevel problems tractable. We identify two classes of growth conditions on the lower-level objective that leads to continuity. Under these assumptions, we show that the local optimality of the bilevel problem can be defined via the Goldstein stationarity condition of the hyper-objective. We then propose the Inexact Gradient-Free Method (IGFM) to solve the bilevel problem, using an approximate zeroth order oracle that is of independent interest. Our non-asymptotic analysis demonstrates that the proposed method can find a $(\delta, \varepsilon)$ Goldstein stationary point for bilevel problems with a zeroth order oracle complexity that is polynomial in $d, 1/\delta$ and $1/\varepsilon$.
translated by 谷歌翻译
我们考虑最小化高维目标函数的问题,该功能可以包括正则化术语,使用(可能的噪声)评估该功能。这种优化也称为无衍生,零阶或黑匣子优化。我们提出了一个新的$ \ textbf {z} $ feroth - $ \ textbf {o} $ rder $ \ textbf {r} $ ptimization方法,称为zoro。当潜在的梯度大致稀疏时,Zoro需要很少的客观函数评估,以获得降低目标函数的新迭代。我们通过自适应,随机梯度估计器实现这一点,然后是不精确的近端梯度方案。在一个新颖的大致稀疏梯度假设和各种不同的凸面设置下,我们显示了zoro的(理论和实证)收敛速率仅对对数依赖于问题尺寸。数值实验表明,Zoro在合成和实际数据集中优于具有相似假设的现有方法。
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
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.
translated by 谷歌翻译