English
Related papers

Related papers: Depth, Not Data: An Analysis of Hessian Spectral B…

200 papers

Spectral clustering is a celebrated algorithm that partitions objects based on pairwise similarity information. While this approach has been successfully applied to a variety of domains, it comes with limitations. The reason is that there…

Statistics Theory · Mathematics 2018-05-24 Kwangjun Ahn , Kangwook Lee , Changho Suh

Multi-scale design has been considered in recent image super-resolution (SR) works to explore the hierarchical feature information. Existing multi-scale networks aim to build elaborate blocks or progressive architecture for restoration. In…

Image and Video Processing · Electrical Eng. & Systems 2023-05-04 Yuqing Liu , Xinfeng Zhang , Shanshe Wang , Siwei Ma , Wen Gao

The sum of independent Wishart matrices, taken from distributions with unequal covariance matrices, plays a crucial role in multivariate statistics, and has applications in the fields of quantitative finance and telecommunication. However,…

Mathematical Physics · Physics 2014-09-23 Santosh Kumar

Recently, it has been observed that when training a deep neural net with SGD, the majority of the loss landscape's curvature quickly concentrates in a tiny *top* eigenspace of the loss Hessian, which remains largely stable thereafter.…

Machine Learning · Computer Science 2025-04-22 Andres Fernandez , Frank Schneider , Maren Mahsereci , Philipp Hennig

Motivated by a neuroscience application we study the problem of statistical estimation of a high-dimensional covariance matrix with a block structure. The block model embeds a structural assumption: the population of items (neurons) can be…

Methodology · Statistics 2025-03-03 Yunran Chen , Surya T Tokdar , Jennifer M Groh

Spectral properties of random matrices play an important role in statistics, machine learning, communications, and many other areas. Engaging results regarding the convergence of the empirical spectral distribution (ESD) and the…

Statistics Theory · Mathematics 2025-07-08 Zeyan Zhuang , Xin Zhang , Dongfang Xu , Shenghui Song

Percolation threshold of a network is the critical value such that when nodes or edges are randomly selected with probability below the value, the network is fragmented but when the probability is above the value, a giant component…

Social and Information Networks · Computer Science 2017-04-26 Yuan Lin , Wei Chen , Zhongzhi Zhang

In this paper, we investigate the asymptotic behaviors of the extreme eigenvectors in a general spiked covariance matrix, where the dimension and sample size increase proportionally. We eliminate the restrictive assumption of the block…

Statistics Theory · Mathematics 2024-05-15 Zhangni Pu , Xiaozhuo Zhang , Jiang Hu , Zhidong Bai

Deep neural network training often exhibits highly anisotropic loss geometry, where a few sharp dominant Hessian directions coexist with a large flatter bulk. Gradients tend to align disproportionately with these dominant directions,…

Machine Learning · Computer Science 2026-05-28 Tolga Dimlioglu , Kristi Topollai , Anna Choromanska

The largest eigenvalue of the matrix describing a network's contact structure is often important in predicting the behavior of dynamical processes. We extend this notion to hypergraphs and motivate the importance of an analogous eigenvalue,…

Physics and Society · Physics 2022-05-11 Nicholas W. Landry , Juan G. Restrepo

Spectral clustering views the similarity matrix as a weighted graph, and partitions the data by minimizing a graph-cut loss. Since it minimizes the across-cluster similarity, there is no need to model the distribution within each cluster.…

Methodology · Statistics 2023-04-14 Leo L. Duan , Arkaprava Roy

We investigate the impact of degree-degree correlations on the spectra of networks. Even though density distributions exhibit drastic changes depending on the (dis)assortative mixing and the network architecture, the short range…

Physics and Society · Physics 2015-02-06 Sarika Jalan , Alok Yadav

In contrast to the neatly bounded spectra of densely populated large random matrices, sparse random matrices often exhibit unbounded eigenvalue tails on the real and imaginary axis, called Lifshitz tails. In the case of asymmetric matrices,…

Disordered Systems and Neural Networks · Physics 2025-11-07 Pietro Valigi , Joseph W. Baron , Izaak Neri , Giulio Biroli , Chiara Cammarota

Consider $D$ random systems that are modeled by independent $N\times N$ complex Hermitian Wigner matrices. Suppose they are lying on a circle and the neighboring systems interact with each other through a deterministic matrix $A$. We prove…

Probability · Mathematics 2025-02-19 Bertrand Stone , Fan Yang , Jun Yin

We study high-density traffic of information packets on sparse modular networks with scale-free subgraphs. With different statistical measures we distinguish between the free flow and congested regime and point out the role of modules in…

Physics and Society · Physics 2015-05-13 Bosiljka Tadić , Marija Mitrović

We investigate gene interaction networks in various cancer cells by spectral analysis of the adjacency matrices. We observe localization of the networks on hub genes which have extraordinarily many links. The eigenvector centralities take…

Molecular Networks · Quantitative Biology 2019-09-25 Ayumi Kikkawa

Motivated by the intriguing behavior displayed in a dynamic network that models a population of extreme introverts and extroverts (XIE), we consider the spectral properties of ensembles of random split graph adjacency matrices. We discover…

Physics and Society · Physics 2017-12-08 Kevin E. Bassler , R. K. P. Zia

Complex networks with directed, local interactions are ubiquitous in nature, and often occur with probabilistic connections due to both intrinsic stochasticity and disordered environments. Sparse non-Hermitian random matrices arise…

Disordered Systems and Neural Networks · Physics 2019-12-04 Grace H. Zhang , David R. Nelson

The success of deep neural networks largely depends on the statistical structure of the training data. While learning dynamics and generalization on isotropic data are well-established, the impact of pronounced anisotropy on these crucial…

Machine Learning · Statistics 2026-01-13 Taishi Watanabe , Ryo Karakida , Jun-nosuke Teramae

In this article, the joint fluctuations of the extreme eigenvalues and eigenvectors of a large dimensional sample covariance matrix are analyzed when the associated population covariance matrix is a finite-rank perturbation of the identity…

Information Theory · Computer Science 2012-06-20 Romain Couillet , Walid Hachem
‹ Prev 1 4 5 6 7 8 10 Next ›