The Optimal transport (OT) problem is rapidly finding its way into machine learning. Favoring its use are its metric properties. Many problems admit solutions with guarantees only for objects embedded in metric spaces, and the use of non-metrics can complicate solving them. Multi-marginal OT (MMOT) generalizes OT to simultaneously transporting multiple distributions. It captures important relations that are missed if the transport only involves two distributions. Research on MMOT, however, has been focused on its existence, uniqueness, practical algorithms, and the choice of cost functions. There is a lack of discussion on the metric properties of MMOT, which limits its theoretical and practical use. Here, we prove new generalized metric properties for a family of pairwise MMOTs. We first explain the difficulty of proving this via two negative results. Afterward, we prove the MMOTs' metric properties. Finally, we show that the generalized triangle inequality of this family of MMOTs cannot be improved. We illustrate the superiority of our MMOTs over other generalized metrics, and over non-metrics in both synthetic and real tasks.
translated by 谷歌翻译
计算Wassersein BaryCenters(A.K.A.最佳运输重构)是由于数据科学的许多应用,最近引起了相当大的关注的几何问题。虽然存在任何固定维度的多项式时间算法,但所有已知的运行时间都在维度中呈指数级。这是一个开放的问题,无论是这种指数依赖性是否可改进到多项式依赖性。本文证明,除非P = NP,答案是否定的。这揭示了Wassersein的BaryCenter计算的“维度诅咒”,其不会发生最佳运输计算。此外,我们对计算Wassersein的硬度结果延伸到近似计算,看似简单的问题案例,以及在其他最佳运输指标中平均概率分布。
translated by 谷歌翻译
Graph clustering is a fundamental problem in unsupervised learning, with numerous applications in computer science and in analysing real-world data. In many real-world applications, we find that the clusters have a significant high-level structure. This is often overlooked in the design and analysis of graph clustering algorithms which make strong simplifying assumptions about the structure of the graph. This thesis addresses the natural question of whether the structure of clusters can be learned efficiently and describes four new algorithmic results for learning such structure in graphs and hypergraphs. All of the presented theoretical results are extensively evaluated on both synthetic and real-word datasets of different domains, including image classification and segmentation, migration networks, co-authorship networks, and natural language processing. These experimental results demonstrate that the newly developed algorithms are practical, effective, and immediately applicable for learning the structure of clusters in real-world data.
translated by 谷歌翻译
K-MEDIAN和K-MEACE是聚类算法的两个最受欢迎的目标。尽管有密集的努力,但对这些目标的近似性很好地了解,特别是在$ \ ell_p $ -metrics中,仍然是一个重大的开放问题。在本文中,我们在$ \ ell_p $ -metrics中显着提高了文献中已知的近似因素的硬度。我们介绍了一个名为Johnson覆盖假说(JCH)的新假设,这大致断言设定系统上的良好的Max K-Coverage问题难以近似于1-1 / e,即使是成员图形设置系统是Johnson图的子图。然后,我们展示了Cohen-Addad和Karthik引入的嵌入技术的概括(Focs'19),JCH意味着K-MEDIAN和K-MERION在$ \ ell_p $ -metrics中的近似结果的近似值的硬度为近距离对于一般指标获得的人。特别地,假设JCH我们表明很难近似K-Meator目标:$ \ Bullet $离散情况:$ \ ell_1 $ 3.94 - $ \ ell_2中的1.73因素为1.73倍$$ - 这分别在UGC下获得了1.56和1.17的先前因子。 $ \ bullet $持续案例:$ \ ell_1 $ 2210 - $ \ ell_2 $的$ \ ell_1 $ 210。$ \ ell_2 $-metric;这在UGC下获得的$ \ ell_2 $的$ \ ell_2 $的先前因子提高了1.07。对于K-Median目标,我们还获得了类似的改进。此外,我们使用Dinure等人的工作证明了JCH的弱版本。 (Sicomp'05)在超图顶点封面上,恢复Cohen-Addad和Karthik(Focs'19 Focs'19)上面的所有结果(近)相同的不可识别因素,但现在在标准的NP $ \ NEQ $ P假设下(代替UGC)。
translated by 谷歌翻译
We study a family of adversarial multiclass classification problems and provide equivalent reformulations in terms of: 1) a family of generalized barycenter problems introduced in the paper and 2) a family of multimarginal optimal transport problems where the number of marginals is equal to the number of classes in the original classification problem. These new theoretical results reveal a rich geometric structure of adversarial learning problems in multiclass classification and extend recent results restricted to the binary classification setting. A direct computational implication of our results is that by solving either the barycenter problem and its dual, or the MOT problem and its dual, we can recover the optimal robust classification rule and the optimal adversarial strategy for the original adversarial problem. Examples with synthetic and real data illustrate our results.
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
We introduce and analyze NetOTC, a procedure for the comparison and soft alignment of weighted networks. Given two networks and a cost function relating their vertices, NetOTC finds an appropriate coupling of their associated random walks having minimum expected cost. The minimizing cost provides a numerical measure of the difference between the networks, while the optimal transport plan itself provides interpretable, probabilistic alignments of the vertices and edges of the two networks. The cost function employed can be based, for example, on vertex degrees, externally defined features, or Euclidean embeddings. Coupling of the full random walks, rather than their stationary distributions, ensures that NetOTC captures local and global information about the given networks. NetOTC applies to networks of different size and structure, and does not the require specification of free parameters. NetOTC respects edges, in the sense that vertex pairs in the given networks are aligned with positive probability only if they are adjacent in the given networks. We investigate a number of theoretical properties of NetOTC that support its use, including metric properties of the minimizing cost and its connection with short- and long-run average cost. In addition, we introduce a new notion of factor for weighted networks, and establish a close connection between factors and NetOTC. Complementing the theory, we present simulations and numerical experiments showing that NetOTC is competitive with, and sometimes superior to, other optimal transport-based network comparison methods in the literature. In particular, NetOTC shows promise in identifying isomorphic networks using a local (degree-based) cost function.
translated by 谷歌翻译
我们开发了一种高效的随机块模型中的弱恢复算法。该算法与随机块模型的Vanilla版本的最佳已知算法的统计保证匹配。从这个意义上讲,我们的结果表明,随机块模型没有稳健性。我们的工作受到最近的银行,Mohanty和Raghavendra(SODA 2021)的工作,为相应的区别问题提供了高效的算法。我们的算法及其分析显着脱离了以前的恢复。关键挑战是我们算法的特殊优化景观:种植的分区可能远非最佳意义,即完全不相关的解决方案可以实现相同的客观值。这种现象与PCA的BBP相转变的推出效应有关。据我们所知,我们的算法是第一个在非渐近设置中存在这种推出效果的鲁棒恢复。我们的算法是基于凸优化的框架的实例化(与平方和不同的不同),这对于其他鲁棒矩阵估计问题可能是有用的。我们的分析的副产物是一种通用技术,其提高了任意强大的弱恢复算法的成功(输入的随机性)从恒定(或缓慢消失)概率以指数高概率。
translated by 谷歌翻译
随机奇异值分解(RSVD)是用于计算大型数据矩阵截断的SVD的一类计算算法。给定A $ n \ times n $对称矩阵$ \ mathbf {m} $,原型RSVD算法输出通过计算$ \ mathbf {m mathbf {m} $的$ k $引导singular vectors的近似m}^{g} \ mathbf {g} $;这里$ g \ geq 1 $是一个整数,$ \ mathbf {g} \ in \ mathbb {r}^{n \ times k} $是一个随机的高斯素描矩阵。在本文中,我们研究了一般的“信号加上噪声”框架下的RSVD的统计特性,即,观察到的矩阵$ \ hat {\ mathbf {m}} $被认为是某种真实但未知的加法扰动信号矩阵$ \ mathbf {m} $。我们首先得出$ \ ell_2 $(频谱规范)和$ \ ell_ {2 \ to \ infty} $(最大行行列$ \ ell_2 $ norm)$ \ hat {\ hat {\ Mathbf {M}} $和信号矩阵$ \ Mathbf {M} $的真实单数向量。这些上限取决于信噪比(SNR)和功率迭代$ g $的数量。观察到一个相变现象,其中较小的SNR需要较大的$ g $值以保证$ \ ell_2 $和$ \ ell_ {2 \ to \ fo \ infty} $ distances的收敛。我们还表明,每当噪声矩阵满足一定的痕量生长条件时,这些相变发生的$ g $的阈值都会很清晰。最后,我们得出了近似奇异向量的行波和近似矩阵的进入波动的正常近似。我们通过将RSVD的几乎最佳性能保证在应用于三个统计推断问题的情况下,即社区检测,矩阵完成和主要的组件分析,并使用缺失的数据来说明我们的理论结果。
translated by 谷歌翻译
Outier-bubust估计是一个基本问题,已由统计学家和从业人员进行了广泛的研究。在过去的几年中,整个研究领域的融合都倾向于“算法稳定统计”,该统计数据的重点是开发可拖动的异常体 - 固定技术来解决高维估计问题。尽管存在这种融合,但跨领域的研究工作主要彼此断开。本文桥接了有关可认证的异常抗衡器估计的最新工作,该估计是机器人技术和计算机视觉中的几何感知,并在健壮的统计数据中并行工作。特别是,我们适应并扩展了最新结果对可靠的线性回归(适用于<< 50%异常值的低外壳案例)和列表可解码的回归(适用于>> 50%异常值的高淘汰案例)在机器人和视觉中通常发现的设置,其中(i)变量(例如旋转,姿势)属于非convex域,(ii)测量值是矢量值,并且(iii)未知的异常值是先验的。这里的重点是绩效保证:我们没有提出新算法,而是为投入测量提供条件,在该输入测量值下,保证现代估计算法可以在存在异常值的情况下恢复接近地面真相的估计值。这些条件是我们所谓的“估计合同”。除了现有结果的拟议扩展外,我们认为本文的主要贡献是(i)通过指出共同点和差异来统一平行的研究行,(ii)在介绍先进材料(例如,证明总和证明)中的统一行为。对从业者的可访问和独立的演讲,(iii)指出一些即时的机会和开放问题,以发出异常的几何感知。
translated by 谷歌翻译
我们考虑了在高维度中平均分离的高斯聚类混合物的问题。我们是从$ k $身份协方差高斯的混合物提供的样本,使任何两对手段之间的最小成对距离至少为$ \ delta $,对于某些参数$ \ delta> 0 $,目标是恢复这些样本的地面真相聚类。它是分离$ \ delta = \ theta(\ sqrt {\ log k})$既有必要且足以理解恢复良好的聚类。但是,实现这种担保的估计值效率低下。我们提供了在多项式时间内运行的第一算法,几乎符合此保证。更确切地说,我们给出了一种算法,它需要多项式许多样本和时间,并且可以成功恢复良好的聚类,只要分离为$ \ delta = \ oomega(\ log ^ {1/2 + c} k)$ ,任何$ c> 0 $。以前,当分离以k $的分离和可以容忍$ \ textsf {poly}(\ log k)$分离所需的quasi arynomial时间时,才知道该问题的多项式时间算法。我们还将我们的结果扩展到分布的分布式的混合物,该分布在额外的温和假设下满足Poincar \ {e}不等式的分布。我们认为我们相信的主要技术工具是一种新颖的方式,可以隐含地代表和估计分配的​​高度时刻,这使我们能够明确地提取关于高度时刻的重要信息而没有明确地缩小全瞬间张量。
translated by 谷歌翻译
Kernel matrices, as well as weighted graphs represented by them, are ubiquitous objects in machine learning, statistics and other related fields. The main drawback of using kernel methods (learning and inference using kernel matrices) is efficiency -- given $n$ input points, most kernel-based algorithms need to materialize the full $n \times n$ kernel matrix before performing any subsequent computation, thus incurring $\Omega(n^2)$ runtime. Breaking this quadratic barrier for various problems has therefore, been a subject of extensive research efforts. We break the quadratic barrier and obtain $\textit{subquadratic}$ time algorithms for several fundamental linear-algebraic and graph processing primitives, including approximating the top eigenvalue and eigenvector, spectral sparsification, solving linear systems, local clustering, low-rank approximation, arboricity estimation and counting weighted triangles. We build on the recent Kernel Density Estimation framework, which (after preprocessing in time subquadratic in $n$) can return estimates of row/column sums of the kernel matrix. In particular, we develop efficient reductions from $\textit{weighted vertex}$ and $\textit{weighted edge sampling}$ on kernel graphs, $\textit{simulating random walks}$ on kernel graphs, and $\textit{importance sampling}$ on matrices to Kernel Density Estimation and show that we can generate samples from these distributions in $\textit{sublinear}$ (in the support of the distribution) time. Our reductions are the central ingredient in each of our applications and we believe they may be of independent interest. We empirically demonstrate the efficacy of our algorithms on low-rank approximation (LRA) and spectral sparsification, where we observe a $\textbf{9x}$ decrease in the number of kernel evaluations over baselines for LRA and a $\textbf{41x}$ reduction in the graph size for spectral sparsification.
translated by 谷歌翻译
Network data are ubiquitous in modern machine learning, with tasks of interest including node classification, node clustering and link prediction. A frequent approach begins by learning an Euclidean embedding of the network, to which algorithms developed for vector-valued data are applied. For large networks, embeddings are learned using stochastic gradient methods where the sub-sampling scheme can be freely chosen. Despite the strong empirical performance of such methods, they are not well understood theoretically. Our work encapsulates representation methods using a subsampling approach, such as node2vec, into a single unifying framework. We prove, under the assumption that the graph is exchangeable, that the distribution of the learned embedding vectors asymptotically decouples. Moreover, we characterize the asymptotic distribution and provided rates of convergence, in terms of the latent parameters, which includes the choice of loss function and the embedding dimension. This provides a theoretical foundation to understand what the embedding vectors represent and how well these methods perform on downstream tasks. Notably, we observe that typically used loss functions may lead to shortcomings, such as a lack of Fisher consistency.
translated by 谷歌翻译
我们研究了非参数混合模型中的一致性以及回归的密切相关的混合物(也称为混合回归)模型,其中允许回归函数是非参数的,并且假定误差分布是高斯密度的卷积。我们在一般条件下构建统一的一致估计器,同时突出显示了将现有的点一致性结果扩展到均匀结果的几个疼痛点。最终的分析事实并非如此,并且在此过程中开发了几种新颖的技术工具。在混合回归的情况下,我们证明了回归函数的$ l^1 $收敛性,同时允许组件回归函数任意地相交,这带来了其他技术挑战。我们还考虑对一般(即非跨方向)非参数混合物的概括。
translated by 谷歌翻译
假设我们在$ \ mathbb {r} ^ d $和predictor x中的响应变量y在$ \ mathbb {r} ^ d $,以便为$ d \ geq 1 $。在置换或未解释的回归中,我们可以访问x和y上的单独无序数据,而不是在通常回归中的(x,y)-pabes上的数据。到目前为止,在文献中,案件$ d = 1 $已收到关注,请参阅例如近期的纸张和杂草[信息和推理,8,619--717]和Balabdaoui等人。 [J.马赫。学习。 res,22(172),1-60]。在本文中,我们考虑使用$ d \ geq 1 $的一般多变量设置。我们表明回归函数的周期性单调性的概念足以用于置换/未解释的回归模型中的识别和估计。我们在允许的回归设置中研究置换恢复,并在基于Kiefer-WolfoItz的基于代索的计算高效且易用算法[ANN。数学。统计部。,27,887--906]非参数最大似然估计和来自最佳运输理论的技术。我们在高斯噪声的相关均方方向误差误差上提供显式上限。与之前的案件的工作$ d = 1 $一样,置换/未解释的设置涉及潜在的解卷积问题的慢速(对数)收敛率。数值研究证实了我们的理论分析,并表明所提出的方法至少根据上述事先工作中的方法进行了比例,同时在计算复杂性方面取得了大量减少。
translated by 谷歌翻译
Consider the problem of matching two independent i.i.d. samples of size $N$ from two distributions $P$ and $Q$ in $\mathbb{R}^d$. For an arbitrary continuous cost function, the optimal assignment problem looks for the matching that minimizes the total cost. We consider instead in this paper the problem where each matching is endowed with a Gibbs probability weight proportional to the exponential of the negative total cost of that matching. Viewing each matching as a joint distribution with $N$ atoms, we then take a convex combination with respect to the above Gibbs probability measure. We show that this resulting random joint distribution converges, as $N\rightarrow \infty$, to the solution of a variational problem, introduced by F\"ollmer, called the Schr\"odinger problem. We also derive the first two error terms of orders $N^{-1/2}$ and $N^{-1}$, respectively. This gives us central limit theorems for integrated test functions, including for the cost of transport, and second order Gaussian chaos limits when the limiting Gaussian variance is zero. The proofs are based on a novel chaos decomposition of the discrete Schr\"odinger bridge by polynomial functions of the pair of empirical distributions as the first and second order Taylor approximations in the space of measures. This is achieved by extending the Hoeffding decomposition from the classical theory of U-statistics.
translated by 谷歌翻译
本文介绍了一种新的基于仿真的推理程序,以对访问I.I.D. \ samples的多维概率分布进行建模和样本,从而规避明确建模密度函数或设计Markov Chain Monte Carlo的通常方法。我们提出了一个称为可逆的Gromov-monge(RGM)距离的新概念的距离和同构的动机,并研究了RGM如何用于设计新的转换样本,以执行基于模拟的推断。我们的RGM采样器还可以估计两个异质度量度量空间之间的最佳对齐$(\ cx,\ mu,c _ {\ cx})$和$(\ cy,\ cy,\ nu,c _ {\ cy})$从经验数据集中,估计的地图大约将一个量度$ \ mu $推向另一个$ \ nu $,反之亦然。我们研究了RGM距离的分析特性,并在轻度条件下得出RGM等于经典的Gromov-Wasserstein距离。奇怪的是,与Brenier的两极分解结合了连接,我们表明RGM采样器以$ C _ {\ cx} $和$ C _ {\ cy} $的正确选择诱导了强度同构的偏见。研究了有关诱导采样器的收敛,表示和优化问题的统计率。还展示了展示RGM采样器有效性的合成和现实示例。
translated by 谷歌翻译
在图形分析中,经典任务在于(组)节点之间的计算相似度测量。在潜伏空间随机图中,节点与未知的潜变量相关联。然后,可以仅使用图形结构在潜像中直接计算距离的距离。在本文中,我们表明可以始终如一地估算潜在空间中节点组之间的熵正常的最佳运输(OT)距离。我们为成本矩阵扰动提供了熵OT的一般稳定性结果。然后,我们将其应用于随机图的几个例子,例如Graphons或$ \ epsilon $ -Praphy。沿途,我们证明了所谓的通用奇异值阈值估计器的新浓度结果,以及估计歧管上的测地距的距离。
translated by 谷歌翻译
随机块模型(SBM)是一个随机图模型,其连接不同的顶点组不同。它被广泛用作研究聚类和社区检测的规范模型,并提供了肥沃的基础来研究组合统计和更普遍的数据科学中出现的信息理论和计算权衡。该专着调查了最近在SBM中建立社区检测的基本限制的最新发展,无论是在信息理论和计算方案方面,以及各种恢复要求,例如精确,部分和弱恢复。讨论的主要结果是在Chernoff-Hellinger阈值中进行精确恢复的相转换,Kesten-Stigum阈值弱恢复的相变,最佳的SNR - 单位信息折衷的部分恢复以及信息理论和信息理论之间的差距计算阈值。该专着给出了在寻求限制时开发的主要算法的原则推导,特别是通过绘制绘制,半定义编程,(线性化)信念传播,经典/非背带频谱和图形供电。还讨论了其他块模型的扩展,例如几何模型和一些开放问题。
translated by 谷歌翻译
我们考虑从数据学习树结构ising模型的问题,使得使用模型计算的后续预测是准确的。具体而言,我们的目标是学习一个模型,使得小组变量$ S $的后海报$ p(x_i | x_s)$。自推出超过50年以来,有效计算最大似然树的Chow-Liu算法一直是学习树结构图形模型的基准算法。 [BK19]示出了关于以预测的局部总变化损耗的CHOW-LIU算法的样本复杂性的界限。虽然这些结果表明,即使在恢复真正的基础图中也可以学习有用的模型是不可能的,它们的绑定取决于相互作用的最大强度,因此不会达到信息理论的最佳选择。在本文中,我们介绍了一种新的算法,仔细结合了Chow-Liu算法的元素,以便在预测的损失下有效地和最佳地学习树ising模型。我们的算法对模型拼写和对抗损坏具有鲁棒性。相比之下,我们表明庆祝的Chow-Liu算法可以任意次优。
translated by 谷歌翻译