中文
相关论文

相关论文: Nonconvex landscapes for $\mathbf{Z}_2$ synchroniz…

200 篇论文

The angular synchronization problem of estimating a set of unknown angles from their known noisy pairwise differences arises in various applications. It can be reformulated as a optimization problem on graphs involving the graph Laplacian…

最优化与控制 · 数学 2022-09-12 Frank Filbir , Felix Krahmer , Oleh Melnyk

In this paper we derive a moment relaxation for large-scale nonsmooth optimization problems with graphical structure and spherical constraints. In contrast to classical moment relaxations for global polynomial optimization that suffer from…

最优化与控制 · 数学 2023-09-27 Robin Kenis , Emanuel Laude , Panagiotis Patrinos

Graph clustering involves the task of dividing nodes into clusters, so that the edge density is higher within clusters as opposed to across clusters. A natural, classic and popular statistical setting for evaluating solutions to this…

机器学习 · 统计学 2016-11-17 Yudong Chen , Sujay Sanghavi , Huan Xu

This paper concerns the problem of recovering an unknown but structured signal $x \in R^n$ from $m$ quadratic measurements of the form $y_r=|<a_r,x>|^2$ for $r=1,2,...,m$. We focus on the under-determined setting where the number of…

机器学习 · 计算机科学 2017-02-22 Mahdi Soltanolkotabi

The angular synchronization problem is to obtain an accurate estimation (up to a constant additive phase) for a set of unknown angles $\theta_1,...,\theta_n$ from $m$ noisy measurements of their offsets $\theta_i-\theta_j \mod 2\pi$. Of…

谱理论 · 数学 2009-11-20 Amit Singer

We consider the problem of recovering low-rank matrices from random rank-one measurements, which spans numerous applications including covariance sketching, phase retrieval, quantum state tomography, and learning shallow polynomial neural…

信息论 · 计算机科学 2018-12-04 Yuanxin Li , Cong Ma , Yuxin Chen , Yuejie Chi

Graph matching or quadratic assignment, is the problem of labeling the vertices of two graphs so that they are as similar as possible. A common method for approximately solving the NP-hard graph matching problem is relaxing it to a convex…

最优化与控制 · 数学 2017-05-23 Nadav Dym

We study the non-convex optimization landscape for maximum likelihood estimation in the discrete orbit recovery model with Gaussian noise. This model is motivated by applications in molecular microscopy and image processing, where each…

统计理论 · 数学 2021-03-02 Zhou Fan , Yi Sun , Tianhao Wang , Yihong Wu

We consider the densest $k$-subgraph problem, which seeks to identify the $k$-node subgraph of a given input graph with maximum number of edges. This problem is well-known to be NP-hard, by reduction to the maximum clique problem. We…

最优化与控制 · 数学 2019-04-09 Polina Bombina , Brendan Ames

Many important geometric estimation problems take the form of synchronization over the special Euclidean group: estimate the values of a set of poses given a set of relative measurements between them. This problem is typically formulated as…

机器人学 · 计算机科学 2017-02-07 David M. Rosen , Luca Carlone , Afonso S. Bandeira , John J. Leonard

This paper studies noisy low-rank matrix completion: given partial and noisy entries of a large low-rank matrix, the goal is to estimate the underlying matrix faithfully and efficiently. Arguably one of the most popular paradigms to tackle…

机器学习 · 统计学 2019-10-08 Yuxin Chen , Yuejie Chi , Jianqing Fan , Cong Ma , Yuling Yan

Consider the community detection problem in random hypergraphs under the non-uniform hypergraph stochastic block model (HSBM), where each hyperedge appears independently with some given probability depending only on the labels of its…

统计理论 · 数学 2024-08-29 Ioana Dumitriu , Haixiao Wang

This paper addresses the Graph Matching problem, which consists of finding the best possible alignment between two input graphs, and has many applications in computer vision, network deanonymization and protein alignment. A common approach…

机器学习 · 统计学 2024-08-12 Ernesto Araya Valdivia , Hemant Tyagi

Motivated by a geometric problem, we introduce a new non-convex graph partitioning objective where the optimality criterion is given by the sum of the Dirichlet eigenvalues of the partition components. A relaxed formulation is identified…

最优化与控制 · 数学 2016-03-29 Braxton Osting , Chris D. White , Edouard Oudet

Low-rank matrix recovery can be solved to statistical optimality by convex matrix optimization under the classical assumption of restricted isometry property (RIP). However, for large problems, the convex formulation is commonly replaced by…

最优化与控制 · 数学 2026-04-22 Andrew D. McRae , Richard Y. Zhang

The synchronization problem over the special orthogonal group $SO(d)$ consists of estimating a set of unknown rotations $R_1,R_2,...,R_n$ from noisy measurements of a subset of their pairwise ratios $R_{i}^{-1}R_{j}$. The problem has found…

信息论 · 计算机科学 2013-07-17 Lanhui Wang , Amit Singer

We investigate the effectiveness of convex relaxation and nonconvex optimization in solving bilinear systems of equations under two different designs (i.e.$~$a sort of random Fourier design and Gaussian design). Despite the wide…

机器学习 · 统计学 2021-07-14 Yuxin Chen , Jianqing Fan , Bingyan Wang , Yuling Yan

We investigate the problem of exact cluster recovery using oracle queries. Previous results show that clusters in Euclidean spaces that are convex and separated with a margin can be reconstructed exactly using only $O(\log n)$ same-cluster…

机器学习 · 计算机科学 2021-07-14 Marco Bressan , Nicolò Cesa-Bianchi , Silvio Lattanzi , Andrea Paudice

Matching and partitioning problems are fundamentals of computer vision applications with examples in multilabel segmentation, stereo estimation and optical-flow computation. These tasks can be posed as non-convex energy minimization…

计算机视觉与模式识别 · 计算机科学 2020-09-14 Jonas Geiping , Fjedor Gaede , Hartmut Bauermeister , Michael Moeller

Random graph alignment refers to recovering the underlying vertex correspondence between two random graphs with correlated edges. This can be viewed as an average-case and noisy version of the well-known graph isomorphism problem. For the…

机器学习 · 统计学 2021-08-18 Luca Ganassali , Laurent Massoulié , Marc Lelarge