本文研究了在{ \em小簇}存在下的种植簇模型中的图聚类问题。传统的结果表明,对于可证明正确地恢复簇的算法,{ \em all}簇必须足够大(特别是,$\tildeΩ(\sqrt{n})$,其中$n$是图的节点数)。我们证明了这并不是一个真正的限制:通过对Jalali et al.(2011)和Chen et al.(2012)提出的基于迹范数的恢复方法进行更精细的分析,我们证明了在某些温和的假设下,小集群不会阻碍大集群的恢复。基于这个结果,我们进一步设计了一个迭代算法来通过“剥离策略”恢复{ \em几乎所有的簇},即,首先恢复大的群集,从而减少问题,然后重复此过程。这些结果被扩展到{ \em partial observation}设置,在该设置中,仅观察图的(选择的)部分。剥离策略产生主动学习算法,在该算法中,随着学习(和移除)大聚类,更频繁地查询与较小聚类相邻的边缘。从高层次上,本文通过提出一个结构化矩阵学习问题,对高维统计和学习结构化数据提出了新的见解,对于这个问题,一次凸松弛方法必然失败,但精心构造的凸松弛序列可以完成这项工作。
英文摘要:
This paper investigates graph clustering in the planted cluster model in the presence of {\em small clusters}. Traditional results dictate that for an algorithm to provably correctly recover the clusters, {\em all} clusters must be sufficiently large (in particular, $\tildeΩ(\sqrt{n})$ where $n$ is the number of nodes of the graph). We show that this is not really a restriction: by a more refined analysis of the trace-norm based recovery approach proposed in Jalali et al. (2011) and Chen et al. (2012), we prove that small clusters, under certain mild assumptions, do not hinder recovery of large ones.
Based on this result, we further devise an iterative algorithm to recover {\em almost all clusters} via a "peeling strategy", i.e., recover large clusters first, leading to a reduced problem, and repeat this procedure. These results are extended to the {\em partial observation} setting, in which only a (chosen) part of the graph is observed.The peeling strategy gives rise to an active learning algorithm, in which edges adjacent to smaller clusters are queried more often as large clusters are learned (and removed).
From a high level, this paper sheds novel insights on high-dimensional statistics and learning structured data, by presenting a structured matrix learning problem for which a one shot convex relaxation approach necessarily fails, but a carefully constructed sequence of convex relaxationsdoes the job.
Breaking the Nonsmooth Barrier: A Scalable Parallel Method for Composite Optimization
École normale supérieure(巴黎高等师范学院);CNRS(法国国家科学研究中心);PSL Research University(巴黎文理研究大学);INRIA(法国国家信息与自动化研究所);ENS(巴黎高等师范学院);MILA(蒙特利尔学习算法研究所);DIRO(蒙特利尔大学计算机科学与运筹学系);Université de Montréal(蒙特利尔大学)
Breaking the Computation and Communication Abstraction Barrier in Distributed Machine Learning Workloads
University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校);Ohio State University(俄亥俄州立大学);Chinese Academy of Sciences(中国科学院);University of California, Riverside(加州大学河滨分校);Microsoft Research(微软研究院)
Breaking the Tuning Barrier: Zero-Hyperparameters Yield Multi-Corner Analysis Via Learned Priors
School of Mathematical and Physical Science, University of Sheffield(谢菲尔德大学数学与物理科学学院);SZU–UoS Joint Centre for Innovation and Entrepreneurship, College of Mechatronics and Control Engineering, Shenzhen University(深大-乌兹别克斯坦联合创新与创业中心,机电控制工程学院,深圳大学);Nanjing University of Science and Technology(南京理工大学)
Breaking the Data Barrier in Learning Symbolic Computation: A Case Study on Variable Ordering Suggestion for Cylindrical Algebraic Decomposition
School of Mathematical Sciences, Jiangsu University(江苏大学数学科学学院);Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences(中国科学院重庆绿色智能技术研究所);Chongqing School, University of Chinese Academy of Sciences(中国科学院大学重庆学院)