中文
相关论文

相关论文: The power of sum-of-squares for detecting hidden s…

200 篇论文

The Sum-of-Squares (SoS) hierarchy of semidefinite programs is a powerful algorithmic paradigm which captures state-of-the-art algorithmic guarantees for a wide array of problems. In the average case setting, SoS lower bounds provide strong…

计算复杂性 · 计算机科学 2021-11-18 Chris Jones , Aaron Potechin , Goutham Rajendran , Madhur Tulsiani , Jeff Xu

One fundamental goal of high-dimensional statistics is to detect or recover planted structure (such as a low-rank matrix) hidden in noisy data. A growing body of work studies low-degree polynomials as a restricted model of computation for…

统计理论 · 数学 2022-06-22 Tselil Schramm , Alexander S. Wein

We consider two problems that arise in machine learning applications: the problem of recovering a planted sparse vector in a random linear subspace and the problem of decomposing a random low-rank overcomplete 3-tensor. For both problems,…

数据结构与算法 · 计算机科学 2016-02-04 Samuel B. Hopkins , Tselil Schramm , Jonathan Shi , David Steurer

We develop new tools in the theory of nonlinear random matrices and apply them to study the performance of the Sum of Squares (SoS) hierarchy on average-case problems. The SoS hierarchy is a powerful optimization technique that has achieved…

计算复杂性 · 计算机科学 2023-02-10 Goutham Rajendran

Given a large data matrix $A\in\mathbb{R}^{n\times n}$, we consider the problem of determining whether its entries are i.i.d. with some known marginal distribution $A_{ij}\sim P_0$, or instead $A$ contains a principal submatrix $A_{{\sf…

计算复杂性 · 计算机科学 2015-02-24 Yash Deshpande , Andrea Montanari

Finding cliques in random graphs and the closely related "planted" clique variant, where a clique of size k is planted in a random G(n, 1/2) graph, have been the focus of substantial study in algorithm design. Despite much effort, the best…

计算复杂性 · 计算机科学 2015-03-24 Raghu Meka , Aaron Potechin , Avi Wigderson

We study computational limitations in \emph{multi-plant} average-case inference problems, in which $t$ disjoint planted structures of size $k$ are embedded in a random background on $n$ elements. A natural parameter in this setting is the…

计算复杂性 · 计算机科学 2026-04-09 Matvey Mosievskiy , Lev Reyzin

Spectral algorithms are an important building block in machine learning and graph algorithms. We are interested in studying when such algorithms can be applied directly to provide optimal solutions to inference tasks. Previous works by…

数据结构与算法 · 计算机科学 2022-10-13 Souvik Dhara , Julia Gaudio , Elchanan Mossel , Colin Sandon

Global polynomial optimization is an important tool across applied mathematics, with many applications in operations research, engineering, and physical sciences. In various settings, the polynomials depend on external parameters that may…

最优化与控制 · 数学 2024-06-14 Richard L. Zhu , Mathias Oster , Yuehaw Khoo

This paper establishes a statistical versus computational trade-off for solving a basic high-dimensional machine learning problem via a basic convex relaxation method. Specifically, we consider the {\em Sparse Principal Component Analysis}…

机器学习 · 计算机科学 2015-10-20 Tengyu Ma , Avi Wigderson

We develop fast spectral algorithms for tensor decomposition that match the robustness guarantees of the best known polynomial-time algorithms for this problem based on the sum-of-squares (SOS) semidefinite programming hierarchy. Our…

机器学习 · 计算机科学 2017-06-28 Tselil Schramm , David Steurer

Clustering is a fundamental primitive in unsupervised learning which gives rise to a rich class of computationally-challenging inference tasks. In this work, we focus on the canonical task of clustering d-dimensional Gaussian mixtures with…

机器学习 · 计算机科学 2022-01-10 Ilias Zadik , Min Jae Song , Alexander S. Wein , Joan Bruna

The Sum-of-Squares (SoS) hierarchy is a semi-definite programming meta-algorithm that captures state-of-the-art polynomial time guarantees for many optimization problems such as Max-$k$-CSPs and Tensor PCA. On the flip side, a SoS lower…

计算复杂性 · 计算机科学 2020-09-07 Mrinalkanti Ghosh , Fernando Granha Jeronimo , Chris Jones , Aaron Potechin , Goutham Rajendran

We present a general approach to rounding semidefinite programming relaxations obtained by the Sum-of-Squares method (Lasserre hierarchy). Our approach is based on using the connection between these relaxations and the Sum-of-Squares proof…

数据结构与算法 · 计算机科学 2013-12-24 Boaz Barak , Jonathan Kelner , David Steurer

A widely used method for solving SOS (Sum Of Squares) decomposition problem is to reduce it to the problem of semi-definite programs (SDPs) which can be efficiently solved in theory. In practice, although many SDP solvers can work out some…

符号计算 · 计算机科学 2018-01-31 Haokun Li , Bican Xia

Given a graph and an integer $k$, Densest $k$-Subgraph is the algorithmic task of finding the subgraph on $k$ vertices with the maximum number of edges. This is a fundamental problem that has been subject to intense study for decades, with…

计算复杂性 · 计算机科学 2023-03-31 Chris Jones , Aaron Potechin , Goutham Rajendran , Jeff Xu

Sum of squares (SOS) optimization is a powerful technique for solving problems where the positivity of a polynomials must be enforced. The common approach to solve an SOS problem is by relaxation to a Semidefinite Program (SDP). The main…

最优化与控制 · 数学 2024-10-29 Daniel Keren , Margarita Osadchy , Roi Poranne

It is well-known that any sum of squares (SOS) program can be cast as a semidefinite program (SDP) of a particular structure and that therein lies the computational bottleneck for SOS programs, as the SDPs generated by this procedure are…

最优化与控制 · 数学 2017-10-05 Amir Ali Ahmadi , Georgina Hall , Antonis Papachristodoulou , James Saunderson , Yang Zheng

The sum-of-squares (SoS) hierarchy is a powerful technique based on semi-definite programming that can be used for both classical and quantum optimization problems. This hierarchy goes under several names; in particular, in quantum…

强关联电子 · 物理学 2024-06-07 Matthew B. Hastings

We present an efficient algorithm to solve semirandom planted instances of any Boolean constraint satisfaction problem (CSP). The semirandom model is a hybrid between worst-case and average-case input models, where the input is generated by…

计算复杂性 · 计算机科学 2023-10-02 Venkatesan Guruswami , Jun-Ting Hsieh , Pravesh K. Kothari , Peter Manohar
‹ 上一页 1 2 3 10 下一页 ›