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.

这项工作研究了经典的光谱群集算法，该算法嵌入了某些图$ g =（v_g，e_g）$的顶点，使用$ g $的某些矩阵的$ k $ eigenVectors纳入$ \ m athbb {r}^k $k $ - 分区$ v_g $ to $ k $簇。我们的第一个结果是对光谱聚类的性能进行更严格的分析，并解释了为什么它在某些条件下的作用比文献中研究的弱点要弱得多。对于第二个结果，我们表明，通过应用少于$ k $的特征向量来构建嵌入，光谱群集能够在许多实际情况下产生更好的输出；该结果是光谱聚类中的第一个结果。除了其概念性和理论意义外，我们工作的实际影响还通过对合成和现实世界数据集的经验分析证明，其中光谱聚类会产生可比或更好的结果，而较少$ k $ k $ eigenVectors。

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.

分层聚类研究将数据集的递归分区设置为连续较小尺寸的簇，并且是数据分析中的基本问题。在这项工作中，我们研究了Dasgupta引入的分层聚类的成本函数，并呈现了两个多项式时间近似算法：我们的第一个结果是高度电导率图的$ O（1）$ - 近似算法。我们简单的建筑绕过了在文献中已知的稀疏切割的复杂递归常规。我们的第二个和主要结果是一个US（1）$ - 用于展示群集明确结构的宽族图形的近似算法。该结果推出了以前的最先进的，该现有技术仅适用于从随机模型产生的图表。通过对合成和现实世界数据集的实证分析，我们所呈现的算法的实证分析表明了我们的工作的重要性，以其具有明确定义的集群结构的先前所提出的图表算法。

In recent years, spectral clustering has become one of the most popular modern clustering algorithms. It is simple to implement, can be solved efficiently by standard linear algebra software, and very often outperforms traditional clustering algorithms such as the k-means algorithm. On the first glance spectral clustering appears slightly mysterious, and it is not obvious to see why it works at all and what it really does. The goal of this tutorial is to give some intuition on those questions. We describe different graph Laplacians and their basic properties, present the most common spectral clustering algorithms, and derive those algorithms from scratch by several different approaches. Advantages and disadvantages of the different spectral clustering algorithms are discussed.

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。

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。

The stochastic block model (SBM) is a random graph model with planted clusters. It is widely employed as a canonical model to study clustering and community detection, and provides generally a fertile ground to study the statistical and computational tradeoffs that arise in network and data sciences.This note surveys the recent developments that establish the fundamental limits for community detection in the SBM, both with respect to information-theoretic and computational thresholds, and for various recovery requirements such as exact, partial and weak recovery (a.k.a., detection). The main results discussed are the phase transitions for exact recovery at the Chernoff-Hellinger threshold, the phase transition for weak recovery at the Kesten-Stigum threshold, the optimal distortion-SNR tradeoff for partial recovery, the learning of the SBM parameters and the gap between information-theoretic and computational thresholds.The note also covers some of the algorithms developed in the quest of achieving the limits, in particular two-round algorithms via graph-splitting, semi-definite programming, linearized belief propagation, classical and nonbacktracking spectral methods. A few open problems are also discussed.

In this work we study statistical properties of graph-based algorithms for multi-manifold clustering (MMC). In MMC the goal is to retrieve the multi-manifold structure underlying a given Euclidean data set when this one is assumed to be obtained by sampling a distribution on a union of manifolds $\mathcal{M} = \mathcal{M}_1 \cup\dots \cup \mathcal{M}_N$ that may intersect with each other and that may have different dimensions. We investigate sufficient conditions that similarity graphs on data sets must satisfy in order for their corresponding graph Laplacians to capture the right geometric information to solve the MMC problem. Precisely, we provide high probability error bounds for the spectral approximation of a tensorized Laplacian on $\mathcal{M}$ with a suitable graph Laplacian built from the observations; the recovered tensorized Laplacian contains all geometric information of all the individual underlying manifolds. We provide an example of a family of similarity graphs, which we call annular proximity graphs with angle constraints, satisfying these sufficient conditions. We contrast our family of graphs with other constructions in the literature based on the alignment of tangent planes. Extensive numerical experiments expand the insights that our theory provides on the MMC problem.

马尔可夫链是一类概率模型，在定量科学中已广泛应用。这部分是由于它们的多功能性，但是可以通过分析探测的便利性使其更加复杂。本教程为马尔可夫连锁店提供了深入的介绍，并探索了它们与图形和随机步行的联系。我们利用从线性代数和图形论的工具来描述不同类型的马尔可夫链的过渡矩阵，特别着眼于探索与这些矩阵相对应的特征值和特征向量的属性。提出的结果与机器学习和数据挖掘中的许多方法有关，我们在各个阶段描述了这些方法。本文并没有本身就成为一项新颖的学术研究，而是提出了一些已知结果的集合以及一些新概念。此外，该教程的重点是向读者提供直觉，而不是正式的理解，并且仅假定对线性代数和概率理论的概念的基本曝光。因此，来自各种学科的学生和研究人员可以访问它。

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.

社交网络通常是使用签名图对社交网络进行建模的，其中顶点与用户相对应，并且边缘具有一个指示用户之间的交互作用的符号。出现的签名图通常包含一个清晰的社区结构，因为该图可以分配到少数极化社区中，每个群落都定义了稀疏切割，并且不可分割地分为较小的极化亚共同体。我们为具有如此清晰的社区结构的签名图提供了本地聚类甲骨文图的小部分。正式地，当图形具有最高度且社区数量最多为$ o（\ log n）$时，则使用$ \ tilde {o}（\ sqrt {n} \ sqrt {n} \ propatatorName {poly}（1/\ varepsilon） ）$预处理时间，我们的Oracle可以回答$ \ tilde {o}（\ sqrt {n} \ operatorname {poly}（1/\ varepsilon））$ time的每个成员查询，并且它正确地分类了$（1--1-（1-） \ varepsilon）$ - 顶点W.R.T.的分数一组隐藏的种植地面真实社区。我们的Oracle在仅需要少数顶点需要的聚类信息的应用中是可取的。以前，此类局部聚类牙齿仅因无符号图而闻名。我们对签名图的概括需要许多新的想法，并对随机步行的行为进行了新的光谱分析。我们评估了我们的算法，用于在合成和现实世界数据集上构建这种甲骨文和回答成员资格查询，从而在实践中验证其性能。

The Forster transform is a method of regularizing a dataset by placing it in {\em radial isotropic position} while maintaining some of its essential properties. Forster transforms have played a key role in a diverse range of settings spanning computer science and functional analysis. Prior work had given {\em weakly} polynomial time algorithms for computing Forster transforms, when they exist. Our main result is the first {\em strongly polynomial time} algorithm to compute an approximate Forster transform of a given dataset or certify that no such transformation exists. By leveraging our strongly polynomial Forster algorithm, we obtain the first strongly polynomial time algorithm for {\em distribution-free} PAC learning of halfspaces. This learning result is surprising because {\em proper} PAC learning of halfspaces is {\em equivalent} to linear programming. Our learning approach extends to give a strongly polynomial halfspace learner in the presence of random classification noise and, more generally, Massart noise.

图形上的分层聚类是数据挖掘和机器学习中的一项基本任务，并在系统发育学，社交网络分析和信息检索等领域中进行了应用。具体而言，我们考虑了由于Dasgupta引起的层次聚类的最近普及的目标函数。以前（大约）最小化此目标函数的算法需要线性时间/空间复杂性。在许多应用程序中，底层图的大小可能很大，即使使用线性时间/空间算法，也可以在计算上具有挑战性。结果，人们对设计只能使用sublinear资源执行全局计算的算法有浓厚的兴趣。这项工作的重点是在三个经过良好的sublinear计算模型下研究大量图的层次聚类，分别侧重于时空，时间和通信，作为要优化的主要资源：（1）（动态）流模型。边缘作为流，（2）查询模型表示，其中使用邻居和度查询查询图形，（3）MPC模型，其中图边缘通过通信通道连接的几台机器进行了分区。我们在上面的所有三个模型中设计用于层次聚类的sublinear算法。我们算法结果的核心是图表中的剪切方面的视图，这使我们能够使用宽松的剪刀示意图进行分层聚类，同时仅引入目标函数中的较小失真。然后，我们的主要算法贡献是如何在查询模型和MPC模型中有效地构建所需形式的切割稀疏器。我们通过建立几乎匹配的下限来补充我们的算法结果，该界限排除了在每个模型中设计更好的算法的可能性。

随着大型网络在重要领域的相关领域的相关性，例如对疾病传播的联系网络的研究，或社交网络对地缘政治的影响，已经有必要研究可扩展到非常大的网络的机器学习工具，通常包含数百万节点。一种主要类别可扩展算法称为网络表示学习或网络嵌入。这些算法尝试通过首次运行多个随机散步，然后使用观察到的随机步行段中的每对节点的共同数量来学习网络功能（例如〜节点）的表示，以获得一些节点的低维表示欧几里德空间。本文的目的是严格地了解两个主要算法，深途化和Node2VEC的性能，以恢复与地面真理社区的规范网络模型的社区。根据图的稀疏性，我们发现所需的随机步道段的长度，使得相应的观察到的共生窗口能够对底层社区分配的几乎精确恢复。我们证明，考虑到一些固定的共同发生窗口，使用随机散步的Node2Vec与低横向概率的随机散步可以相比，与使用简单随机散步的深度扫视相比，稀疏网络可以成功。此外，如果稀疏参数低，我们提供了证据表明这些算法几乎完全恢复可能不会成功。该分析需要开发用于对具有底层低级结构的随机网络计数的通用工具，这与独立兴趣。

光谱聚类在从业者和理论家中都很受欢迎。尽管对光谱聚类的性能保证有充分的了解，但最近的研究集中于在群集中执行``公平''，要求它们在分类敏感的节点属性方面必须``平衡''人口中的种族分布）。在本文中，我们考虑了一个设置，其中敏感属性间接表现在辅助\ textit {表示图}中，而不是直接观察到。该图指定了可以相对于敏感属性互相表示的节点对，除了通常的\ textit {相似性图}外，还可以观察到。我们的目标是在相似性图中找到簇，同时尊重由表示图编码的新个人公平性约束。我们为此任务开发了不均衡和归一化光谱聚类的变体，并在代表图诱导的种植分区模型下分析其性能。该模型同时使用节点的群集成员身份和表示图的结构来生成随机相似性图。据我们所知，这些是在个人级别的公平限制下受约束光谱聚类的第一个一致性结果。数值结果证实了我们的理论发现。

Low-rank matrix approximations, such as the truncated singular value decomposition and the rank-revealing QR decomposition, play a central role in data analysis and scientific computing. This work surveys and extends recent research which demonstrates that randomization offers a powerful tool for performing low-rank matrix approximation. These techniques exploit modern computational architectures more fully than classical methods and open the possibility of dealing with truly massive data sets.This paper presents a modular framework for constructing randomized algorithms that compute partial matrix decompositions. These methods use random sampling to identify a subspace that captures most of the action of a matrix. The input matrix is then compressed-either explicitly or implicitly-to this subspace, and the reduced matrix is manipulated deterministically to obtain the desired low-rank factorization. In many cases, this approach beats its classical competitors in terms of accuracy, speed, and robustness. These claims are supported by extensive numerical experiments and a detailed error analysis.The specific benefits of randomized techniques depend on the computational environment. Consider the model problem of finding the k dominant components of the singular value decomposition of an m × n matrix. (i) For a dense input matrix, randomized algorithms require O(mn log(k)) floating-point operations (flops) in contrast with O(mnk) for classical algorithms. (ii) For a sparse input matrix, the flop count matches classical Krylov subspace methods, but the randomized approach is more robust and can easily be reorganized to exploit multi-processor architectures. (iii) For a matrix that is too large to fit in fast memory, the randomized techniques require only a constant number of passes over the data, as opposed to O(k) passes for classical algorithms. In fact, it is sometimes possible to perform matrix approximation with a single pass over the data.

我们提出了改进的算法，并为身份测试$ n $维分布的问题提供了统计和计算下限。在身份测试问题中，我们将作为输入作为显式分发$ \ mu $，$ \ varepsilon> 0 $，并访问对隐藏分布$ \ pi $的采样甲骨文。目标是区分两个分布$ \ mu $和$ \ pi $是相同的还是至少$ \ varepsilon $ -far分开。当仅从隐藏分布$ \ pi $中访问完整样本时，众所周知，可能需要许多样本，因此以前的作品已经研究了身份测试，并额外访问了各种有条件采样牙齿。我们在这里考虑一个明显弱的条件采样甲骨文，称为坐标Oracle，并在此新模型中提供了身份测试问题的相当完整的计算和统计表征。我们证明，如果一个称为熵的分析属性为可见分布$ \ mu $保留，那么对于任何使用$ \ tilde {o}（n/\ tilde {o}），有一个有效的身份测试算法Varepsilon）$查询坐标Oracle。熵的近似张力是一种经典的工具，用于证明马尔可夫链的最佳混合时间边界用于高维分布，并且最近通过光谱独立性为许多分布族建立了最佳的混合时间。我们将算法结果与匹配的$ \ omega（n/\ varepsilon）$统计下键进行匹配的算法结果补充，以供坐标Oracle下的查询数量。我们还证明了一个计算相变：对于$ \ {+1，-1，-1 \}^n $以上的稀疏抗抗铁磁性模型，在熵失败的近似张力失败的状态下，除非RP = np，否则没有有效的身份测试算法。

我们研究了学习哈密顿$ h $ to precision $ \ varepsilon $的问题，假设我们将获得其gibbs state $ \ rho = \ exp（ - \ beta h）/\ operatoratorname {tr}（\ exp（\ exp）（ - \ beta h））$在已知的反温度$ \ beta $处。 Anshu，Arunachalam，Kuwahara和Soleimanifar（Nature Physics，2021，Arxiv：2004.07266）最近研究了此问题的样品复杂性（需要$ \ rho $的副本数量）。在高温（低$ \ beta $）制度中，他们的算法具有样品复杂性poly poly $（n，1/\ beta，1/\ varepsilon）$，并且可以用多项式但次优的时间复杂性实现。在本文中，我们研究了更一般的哈密顿人的同样问题。我们展示了如何学习哈密顿量的系数到错误$ \ varepsilon $带有样本复杂性$ s = o（\ log n/（\ beta \ varepsilon）^{2}）$和样本大小的时间复杂性，$ o（s n）$。此外，我们证明了匹配的下限，表明我们算法的样品复杂性是最佳的，因此我们的时间复杂性也是最佳的。在附录中，我们证明，几乎可以使用相同的算法来从实时进化的统一$ e^{ - it H} $中学习$ h $，其中具有相似的示例和时间复杂性的小$ t $制度。

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）。