中文
相关论文

相关论文: Hidden Integrality and Semi-random Robustness of S…

200 篇论文

We study the statistical performance of semidefinite programming (SDP) relaxations for clustering under random graph models. Under the $\mathbb{Z}_{2}$ Synchronization model, Censored Block Model and Stochastic Block Model, we show that SDP…

统计理论 · 数学 2019-04-23 Yingjie Fei , Yudong Chen

We study graph clustering in the Stochastic Block Model (SBM) in the presence of both large clusters and small, unrecoverable clusters. Previous convex relaxation approaches achieving exact recovery do not allow any small clusters of size…

机器学习 · 计算机科学 2025-02-25 Matthew Zurek , Yudong Chen

In this paper we consider the cluster estimation problem under the Stochastic Block Model. We show that the semidefinite programming (SDP) formulation for this problem achieves an error rate that decays exponentially in the signal-to-noise…

机器学习 · 统计学 2017-05-24 Yingjie Fei , Yudong Chen

Resolving a conjecture of Abbe, Bandeira and Hall, the authors have recently shown that the semidefinite programming (SDP) relaxation of the maximum likelihood estimator achieves the sharp threshold for exactly recovering the community…

机器学习 · 统计学 2016-06-16 Bruce Hajek , Yihong Wu , Jiaming Xu

We introduce a model-free relax-and-round algorithm for k-means clustering based on a semidefinite relaxation due to Peng and Wei. The algorithm interprets the SDP output as a denoised version of the original data and then rounds this…

机器学习 · 统计学 2016-05-11 Dustin G. Mixon , Soledad Villar , Rachel Ward

We study a semidefinite programming (SDP) relaxation of the maximum likelihood estimation for exactly recovering a hidden community of cardinality $K$ from an $n \times n$ symmetric data matrix $A$, where for distinct indices $i,j$, $A_{ij}…

机器学习 · 统计学 2016-06-06 Bruce Hajek , Yihong Wu , Jiaming Xu

In this paper, we consider the problem of partitioning a small data sample of size $n$ drawn from a mixture of 2 sub-gaussian distributions in $\R^p$. We consider semidefinite programming relaxations of an integer quadratic program that is…

机器学习 · 统计学 2025-03-19 Shuheng Zhou

Statistical inference problems arising within signal processing, data mining, and machine learning naturally give rise to hard combinatorial optimization problems. These problems become intractable when the dimensionality of the data is…

统计力学 · 物理学 2017-04-27 Adel Javanmard , Andrea Montanari , Federico Ricci-Tersenghi

Many statistical learning problems have recently been shown to be amenable to Semi-Definite Programming (SDP), with community detection and clustering in Gaussian mixture models as the most striking instances [javanmard et al., 2016]. Given…

统计理论 · 数学 2020-04-07 Stéphane Chrétien , Mihai Cucuringu , Guillaume Lecué , Lucie Neirac

Semidefinite programming (SDP) is a powerful tool for tackling a wide range of computationally hard problems such as clustering. Despite the high accuracy, semidefinite programs are often too slow in practice with poor scalability on large…

机器学习 · 统计学 2022-02-10 Yubo Zhuang , Xiaohui Chen , Yun Yang

We investigate the clustering performances of the relaxed $K$means in the setting of sub-Gaussian Mixture Model (sGMM) and Stochastic Block Model (SBM). After identifying the appropriate signal-to-noise ratio (SNR), we prove that the…

统计理论 · 数学 2019-04-22 Christophe Giraud , Nicolas Verzelen

Montanari and Richard (2015) asked whether a natural semidefinite programming (SDP) relaxation can effectively optimize $\mathbf{x}^{\top}\mathbf{W} \mathbf{x}$ over $\|\mathbf{x}\| = 1$ with $x_i \geq 0$ for all coordinates $i$, where…

数据结构与算法 · 计算机科学 2020-12-07 Afonso S. Bandeira , Dmitriy Kunisky , Alexander S. Wein

The stochastic block model (SBM) is a popular tool for community detection in networks, but fitting it by maximum likelihood (MLE) involves a computationally infeasible optimization problem. We propose a new semidefinite programming (SDP)…

机器学习 · 计算机科学 2016-03-17 Arash A. Amini , Elizaveta Levina

Several probabilistic models from high-dimensional statistics and machine learning reveal an intriguing --and yet poorly understood-- dichotomy. Either simple local algorithms succeed in estimating the object of interest, or even…

离散数学 · 计算机科学 2016-10-19 Zhou Fan , Andrea Montanari

We study robust convex quadratic programs where the uncertain problem parameters can contain both continuous and integer components. Under the natural boundedness assumption on the uncertainty set, we show that the generic problems are…

最优化与控制 · 数学 2018-12-19 Areesh Mittal , Can Gokalp , Grani A. Hanasusanto

It is well-known that by adding integrality constraints to the semidefinite programming (SDP) relaxation of the max-cut problem, the resulting integer semidefinite program is an exact formulation of the problem. In this paper we show…

最优化与控制 · 数学 2023-11-09 Frank de Meijer , Renata Sotirov

Consider $N$ points in $\mathbb{R}^d$ and $M$ local coordinate systems that are related through unknown rigid transforms. For each point we are given (possibly noisy) measurements of its local coordinates in some of the coordinate systems.…

计算机视觉与模式识别 · 计算机科学 2014-12-24 Kunal N. Chaudhury , Yuehaw Khoo , Amit Singer

In solving hard computational problems, semidefinite program (SDP) relaxations often play an important role because they come with a guarantee of optimality. Here, we focus on a popular semidefinite relaxation of K-means clustering which…

机器学习 · 计算机科学 2018-09-07 Mariano Tepper , Anirvan M. Sengupta , Dmitri Chklovskii

This paper develops new semidefinite programming (SDP) relaxation techniques for two classes of mixed binary quadratically constrained quadratic programs (MBQCQP) and analyzes their approximation performance. The first class of problem…

最优化与控制 · 数学 2014-03-18 Zi Xu , Mingyi Hong

We consider the NP-hard problem of minimizing a convex quadratic function over the integer lattice ${\bf Z}^n$. We present a simple semidefinite programming (SDP) relaxation for obtaining a nontrivial lower bound on the optimal value of the…

最优化与控制 · 数学 2017-03-16 Jaehyun Park , Stephen Boyd
‹ 上一页 1 2 3 10 下一页 ›