本文调查了一类称为线性互补系统(LCSS)的分段仿射动态系统的学习或系统识别。我们提出了一种基于违规的损失,它可以使用基于梯度的方法在没有先前了解混合模式边界的情况下高效地学习LCS参数化。建议的违规行为损失包括动态预测损失和新的互补性违规损失。我们展示了这种损失制定所获得的几个属性,包括其可分性,第一和二阶衍生物的有效计算,以及其与传统预测损失的关系,严格执行互补性。我们应用基于违规的损失制定,以学习具有数万种(潜在僵硬)混合模式的LCSS。结果表明了识别分段仿射动态的最新能力,优于必须通过非平滑线性互补问题来区分的优势方法。
translated by 谷歌翻译
In contact-rich tasks, like dexterous manipulation, the hybrid nature of making and breaking contact creates challenges for model representation and control. For example, choosing and sequencing contact locations for in-hand manipulation, where there are thousands of potential hybrid modes, is not generally tractable. In this paper, we are inspired by the observation that far fewer modes are actually necessary to accomplish many tasks. Building on our prior work learning hybrid models, represented as linear complementarity systems, we find a reduced-order hybrid model requiring only a limited number of task-relevant modes. This simplified representation, in combination with model predictive control, enables real-time control yet is sufficient for achieving high performance. We demonstrate the proposed method first on synthetic hybrid systems, reducing the mode count by multiple orders of magnitude while achieving task performance loss of less than 5%. We also apply the proposed method to a three-fingered robotic hand manipulating a previously unknown object. With no prior knowledge, we achieve state-of-the-art closed-loop performance in less than five minutes of online learning.
translated by 谷歌翻译
灵感来自近期跨越隐式学习在许多机器人任务的实证效果的程度,我们寻求了解隐式配方的理论优势,面对几乎不连续的功能,用于制造和破坏与环境中的环境接触的系统的共同特征和操纵。我们呈现并激励三种学习功能:一个明确和两个隐含。我们导出这三种方法中的每一个的泛化界限,揭示了基于预测误差损失的显式和隐式方法通常无法产生紧张的界限,与其他具有基于违规的丢失定义的其他隐含方法,这可以基本上更加强大地陡峭连续下坡。此外,我们证明这种违规的隐式损失可以紧密绑定图形距离,通常具有物理根源的数量并在输入和输出中处理噪声,而不是考虑输出噪声的预测损失。我们对违规隐性制剂的普遍性和身体相关性的洞察力与先前作品的匹配证据,并通过玩具问题验证,受到刚性联络模型的启发,并在整个理论分析中引用。
translated by 谷歌翻译
对于函数的矩阵或凸起的正半明确度(PSD)的形状约束在机器学习和科学的许多应用中起着核心作用,包括公制学习,最佳运输和经济学。然而,存在很少的功能模型,以良好的经验性能和理论担保来强制执行PSD-NESS或凸起。在本文中,我们介绍了用于在PSD锥中的值的函数的内核平方模型,其扩展了最近建议编码非负标量函数的内核平方型号。我们为这类PSD函数提供了一个代表性定理,表明它构成了PSD函数的普遍近似器,并在限定的平等约束的情况下导出特征值界限。然后,我们将结果应用于建模凸起函数,通过执行其Hessian的核心量子表示,并表明可以因此表示任何平滑且强凸的功能。最后,我们说明了我们在PSD矩阵值回归任务中的方法以及标准值凸起回归。
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
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
We describe an algorithm that learns two-layer residual units using rectified linear unit (ReLU) activation: suppose the input $\mathbf{x}$ is from a distribution with support space $\mathbb{R}^d$ and the ground-truth generative model is a residual unit of this type, given by $\mathbf{y} = \boldsymbol{B}^\ast\left[\left(\boldsymbol{A}^\ast\mathbf{x}\right)^+ + \mathbf{x}\right]$, where ground-truth network parameters $\boldsymbol{A}^\ast \in \mathbb{R}^{d\times d}$ represent a full-rank matrix with nonnegative entries and $\boldsymbol{B}^\ast \in \mathbb{R}^{m\times d}$ is full-rank with $m \geq d$ and for $\boldsymbol{c} \in \mathbb{R}^d$, $[\boldsymbol{c}^{+}]_i = \max\{0, c_i\}$. We design layer-wise objectives as functionals whose analytic minimizers express the exact ground-truth network in terms of its parameters and nonlinearities. Following this objective landscape, learning residual units from finite samples can be formulated using convex optimization of a nonparametric function: for each layer, we first formulate the corresponding empirical risk minimization (ERM) as a positive semi-definite quadratic program (QP), then we show the solution space of the QP can be equivalently determined by a set of linear inequalities, which can then be efficiently solved by linear programming (LP). We further prove the strong statistical consistency of our algorithm, and demonstrate its robustness and sample efficiency through experimental results on synthetic data and a set of benchmark regression datasets.
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} $中可能不良条件变得不可知。
translated by 谷歌翻译
在本文中,我们提出了SC-REG(自助正规化)来学习过共同的前馈神经网络来学习\ EMPH {牛顿递减}框架的二阶信息进行凸起问题。我们提出了具有自助正规化(得分-GGN)算法的广义高斯 - 牛顿,其每次接收到新输入批处理时都会更新网络参数。所提出的算法利用Hessian矩阵中的二阶信息的结构,从而减少训练计算开销。虽然我们的目前的分析仅考虑凸面的情况,但数值实验表明了我们在凸和非凸面设置下的方法和快速收敛的效率,这对基线一阶方法和准牛顿方法进行了比较。
translated by 谷歌翻译
通过在线规范相关性分析的问题,我们提出了\ emph {随机缩放梯度下降}(SSGD)算法,以最小化通用riemannian歧管上的随机功能的期望。 SSGD概括了投影随机梯度下降的思想,允许使用缩放的随机梯度而不是随机梯度。在特殊情况下,球形约束的特殊情况,在广义特征向量问题中产生的,我们建立了$ \ sqrt {1 / t} $的令人反感的有限样本,并表明该速率最佳最佳,直至具有积极的积极因素相关参数。在渐近方面,一种新的轨迹平均争论使我们能够实现局部渐近常态,其速率与鲁普特 - Polyak-Quaditsky平均的速率匹配。我们将这些想法携带在一个在线规范相关分析,从事文献中的第一次获得了最佳的一次性尺度算法,其具有局部渐近融合到正常性的最佳一次性尺度算法。还提供了用于合成数据的规范相关分析的数值研究。
translated by 谷歌翻译
策略梯度方法适用于复杂的,不理解的,通过对参数化的策略进行随机梯度下降来控制问题。不幸的是,即使对于可以通过标准动态编程技术解决的简单控制问题,策略梯度算法也会面临非凸优化问题,并且被广泛理解为仅收敛到固定点。这项工作确定了结构属性 - 通过几个经典控制问题共享 - 确保策略梯度目标函数尽管是非凸面,但没有次优的固定点。当这些条件得到加强时,该目标满足了产生收敛速率的Polyak-lojasiewicz(梯度优势)条件。当其中一些条件放松时,我们还可以在任何固定点的最佳差距上提供界限。
translated by 谷歌翻译
二重优化发现在现代机器学习问题中发现了广泛的应用,例如超参数优化,神经体系结构搜索,元学习等。而具有独特的内部最小点(例如,内部功能是强烈凸的,都具有唯一的内在最小点)的理解,这是充分理解的,多个内部最小点的问题仍然是具有挑战性和开放的。为此问题设计的现有算法适用于限制情况,并且不能完全保证融合。在本文中,我们采用了双重优化的重新制定来限制优化,并通过原始的双二线优化(PDBO)算法解决了问题。 PDBO不仅解决了多个内部最小挑战,而且还具有完全一阶效率的情况,而无需涉及二阶Hessian和Jacobian计算,而不是大多数现有的基于梯度的二杆算法。我们进一步表征了PDBO的收敛速率,它是与多个内部最小值的双光线优化的第一个已知的非质合收敛保证。我们的实验证明了所提出的方法的预期性能。
translated by 谷歌翻译
Implicit regularization is an important way to interpret neural networks. Recent theory starts to explain implicit regularization with the model of deep matrix factorization (DMF) and analyze the trajectory of discrete gradient dynamics in the optimization process. These discrete gradient dynamics are relatively small but not infinitesimal, thus fitting well with the practical implementation of neural networks. Currently, discrete gradient dynamics analysis has been successfully applied to shallow networks but encounters the difficulty of complex computation for deep networks. In this work, we introduce another discrete gradient dynamics approach to explain implicit regularization, i.e. landscape analysis. It mainly focuses on gradient regions, such as saddle points and local minima. We theoretically establish the connection between saddle point escaping (SPE) stages and the matrix rank in DMF. We prove that, for a rank-R matrix reconstruction, DMF will converge to a second-order critical point after R stages of SPE. This conclusion is further experimentally verified on a low-rank matrix reconstruction problem. This work provides a new theory to analyze implicit regularization in deep learning.
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
我们解决了如何在没有严格缩放条件的情况下实现分布式分数回归中最佳推断的问题。由于分位数回归(QR)损失函数的非平滑性质,这是具有挑战性的,这使现有方法的使用无效。难度通过应用于本地(每个数据源)和全局目标函数的双光滑方法解决。尽管依赖局部和全球平滑参数的精致组合,但分位数回归模型是完全参数的,从而促进了解释。在低维度中,我们为顺序定义的分布式QR估计器建立了有限样本的理论框架。这揭示了通信成本和统计错误之间的权衡。我们进一步讨论并比较了基于WALD和得分型测试和重采样技术的反转的几种替代置信集结构,并详细介绍了对更极端分数系数有效的改进。在高维度中,采用了一个稀疏的框架,其中提出的双滑目标功能与$ \ ell_1 $ -penalty相辅相成。我们表明,相应的分布式QR估计器在近乎恒定的通信回合之后达到了全球收敛率。一项彻底的模拟研究进一步阐明了我们的发现。
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
预测+优化是一个常见的真实范式,在那里我们必须在解决优化问题之前预测问题参数。然而,培训预测模型的标准通常与下游优化问题的目标不一致。最近,已经提出了集中的预测方法,例如Spo +和直接优化,以填补这种差距。但是,它们不能直接处理许多真实目标所需的$最大$算子的软限制。本文提出了一种用于现实世界线性和半定义负二次编程问题的新型分析微弱的代理目标框架,具有软线和非负面的硬度约束。该框架给出了约束乘法器上的理论界限,并导出了关于预测参数的闭合形式解决方案,从而导出问题中的任何变量的梯度。我们在使用软限制扩展的三个应用程序中评估我们的方法:合成线性规划,产品组合优化和资源供应,表明我们的方法优于传统的双阶段方法和其他集中决定的方法。
translated by 谷歌翻译
我们提出了一个基于预测校正范式的统一框架,用于在原始和双空间中的预测校正范式。在此框架中,以固定的间隔进行了连续变化的优化问题,并且每个问题都通过原始或双重校正步骤近似解决。通过预测步骤的输出,该解决方案方法是温暖启动的,该步骤的输出可以使用过去的信息解决未来问题的近似。在不同的假设集中研究并比较了预测方法。该框架涵盖的算法的示例是梯度方法的时变版本,分裂方法和著名的乘数交替方向方法(ADMM)。
translated by 谷歌翻译
最近有兴趣的兴趣在教师学生环境中的各种普遍性线性估计问题中的渐近重建性能研究,特别是对于I.I.D标准正常矩阵的案例。在这里,我们超越这些矩阵,并证明了具有具有任意界限频谱的旋转不变数据矩阵的凸遍的线性模型的重建性能的分析公式,严格地确认使用来自统计物理的副本衍生的猜想。该公式包括许多问题,例如压缩感测或稀疏物流分类。通过利用消息通过算法和迭代的统计特性来实现证明,允许表征估计器的渐近实证分布。我们的证据是基于构建Oracle多层向量近似消息传递算法的会聚序列的构建,其中通过检查等效动态系统的稳定性来完成收敛分析。我们说明了我们对主流学习方法的数值示例的要求,例如稀疏的逻辑回归和线性支持矢量分类器,显示中等大小模拟和渐近预测之间的良好一致性。
translated by 谷歌翻译
We study the task of learning state representations from potentially high-dimensional observations, with the goal of controlling an unknown partially observable system. We pursue a direct latent model learning approach, where a dynamic model in some latent state space is learned by predicting quantities directly related to planning (e.g., costs) without reconstructing the observations. In particular, we focus on an intuitive cost-driven state representation learning method for solving Linear Quadratic Gaussian (LQG) control, one of the most fundamental partially observable control problems. As our main results, we establish finite-sample guarantees of finding a near-optimal state representation function and a near-optimal controller using the directly learned latent model. To the best of our knowledge, despite various empirical successes, prior to this work it was unclear if such a cost-driven latent model learner enjoys finite-sample guarantees. Our work underscores the value of predicting multi-step costs, an idea that is key to our theory, and notably also an idea that is known to be empirically valuable for learning state representations.
translated by 谷歌翻译