English
Related papers

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

200 papers

We introduce a principled approach for unsupervised structure learning of deep neural networks. We propose a new interpretation for depth and inter-layer connectivity where conditional independencies in the input distribution are encoded…

Machine Learning · Statistics 2018-10-18 Raanan Y. Rohekar , Shami Nisimov , Yaniv Gurwicz , Guy Koren , Gal Novik

Hessians of neural network (NN) contain essential information about the curvature of NN loss landscapes which can be used to estimate NN generalization capabilities. We have previously proposed generalization criteria that rely on the…

Machine Learning · Computer Science 2025-04-25 Nikita Gabdullin

We study the spectra and eigenvectors of the adjacency matrices of scale-free networks when bi-directional interaction is allowed, so that the adjacency matrix is real and symmetric. The spectral density shows an exponential decay around…

Statistical Mechanics · Physics 2009-11-07 K. -I. Goh , B. Kahng , D. Kim

Low dimensional structures appear ubiquitously in the eigenspectra of deep learning matrices in classification networks trained in the overparameterized regime. While theoretical advances have aimed to explain this phenomenology, they…

Machine Learning · Computer Science 2026-05-28 Connall Garrod , Jonathan P. Keating

We study the task of clustering in directed networks. We show that using the eigenvalue/eigenvector decomposition of the adjacency matrix is simpler than all common methods which are based on a combination of data regularization and SVD…

Machine Learning · Computer Science 2021-02-08 Simon Coste , Ludovic Stephan

A large variety of dynamical processes that take place on networks can be expressed in terms of the spectral properties of some linear operator which reflects how the dynamical rules depend on the network topology. Often such spectral…

Data Analysis, Statistics and Probability · Physics 2013-08-28 Tiago P. Peixoto

The paper deals with the distribution of singular values of the input-output Jacobian of deep untrained neural networks in the limit of their infinite width. The Jacobian is the product of random matrices where the independent rectangular…

Machine Learning · Statistics 2022-07-13 Leonid Pastur

The lack of theoretical results for Layer Normalization and feedforward Hessians has left a gap in the study of Transformer optimization landscapes. We address this by deriving explicit second-order expressions for these components, thereby…

Machine Learning · Computer Science 2025-10-21 Egor Petrov , Nikita Kiselev , Vladislav Meshkov , Andrey Grabovoy

Looking to overcome the limitations of traditional networks, the network science community has lately given much attention to the so-called higher-order networks, where group interactions are modeled alongside pairwise ones. While degree…

Physics and Society · Physics 2022-07-11 Demival Vasques Filho

Many natural and social systems develop complex networks, that are usually modelled as random graphs. The eigenvalue spectrum of these graphs provides information about their structural properties. While the semi-circle law is known to…

Statistical Mechanics · Physics 2009-11-07 Illes J. Farkas , Imre Derenyi , Albert-Laszlo Barabasi , Tamas Vicsek

The spiked covariance model has gained increasing popularity in high-dimensional data analysis. A fundamental problem is determination of the number of spiked eigenvalues, $K$. For estimation of $K$, most attention has focused on the use of…

Methodology · Statistics 2021-01-07 Zheng Tracy Ke , Yucong Ma , Xihong Lin

Euclidean random matrices arise in a wide range of physical systems where interactions are determined by spatial configurations, including disordered media and cooperative phenomena in atomic ensembles. Unlike classical random matrix…

Statistical Mechanics · Physics 2026-05-08 Pasquale Casaburi , Pierpaolo Vivo

This paper focuses on large neural networks whose synaptic connectivity matrices are randomly chosen from certain random matrix ensembles. The dynamics of these networks can be characterized by the eigenvalue spectra of their connectivity…

Disordered Systems and Neural Networks · Physics 2015-06-05 Yi Wei

In this paper, we study the asymptotic behavior of the extreme eigenvalues and eigenvectors of the high dimensional spiked sample covariance matrices, in the supercritical case when a reliable detection of spikes is possible. Especially, we…

Statistics Theory · Mathematics 2020-09-04 Zhigang Bao , Xiucai Ding , Jingming Wang , Ke Wang

Empirical studies reported that the Hessian matrix of neural networks (NNs) exhibits a near-block-diagonal structure, yet its theoretical foundation remains unclear. In this work, we reveal that the reported Hessian structure comes from a…

Machine Learning · Computer Science 2025-09-23 Zhaorui Dong , Yushun Zhang , Jianfeng Yao , Ruoyu Sun

The spectral properties of the adjacency matrix provide a trove of information about the structure and function of complex networks. In particular, the largest eigenvalue and its associated principal eigenvector are crucial in the…

Physics and Society · Physics 2016-01-14 Romualdo Pastor-Satorras , Claudio Castellano

We revisit the theoretical performances of Spectral Clustering, a classical algorithm for graph partitioning that relies on the eigenvectors of a matrix representation of the graph. Informally, we show that Spectral Clustering works well as…

Machine Learning · Computer Science 2025-12-01 George Tyler , Luca Zanetti

The energy landscape of multiverse cosmology is often modeled by a multi-dimensional random Gaussian potential. The physical predictions of such models crucially depend on the eigenvalue distribution of the Hessian matrix at potential…

High Energy Physics - Theory · Physics 2018-04-04 Masaki Yamada , Alexander Vilenkin

This work investigates the multiplicity and differentiability of eigenfrequencies in structures with various symmetries. In particular, the study explores how the geometric and design variable symmetries affect the distribution of…

Computational Engineering, Finance, and Science · Computer Science 2025-01-28 Shiyao Sun , Kapil Khandelwal

Chaotic behavior or lack thereof in non-Hermitian systems is often diagnosed via spectral analysis of associated complex eigenvalues. Very recently, singular values of the associated non-Hermitian systems have been proposed as an effective…

Statistical Mechanics · Physics 2025-03-18 Mahaveer Prasad , S. Harshini Tekur , Bijay Kumar Agarwalla , Manas Kulkarni