English
Related papers

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

200 papers

Quantifying the eigenvalue spectra of large random matrices allows one to understand the factors that contribute to the stability of dynamical systems with many interacting components. This work explores the effect that the interaction…

Disordered Systems and Neural Networks · Physics 2022-12-08 Joseph W. Baron

The Hessian of neural networks can be decomposed into a sum of two matrices: (i) the positive semidefinite generalized Gauss-Newton matrix G, and (ii) the matrix H containing negative eigenvalues. We observe that for wider networks,…

Machine Learning · Computer Science 2020-01-15 Etai Littwin , Lior Wolf

We investigate how in complex systems the eigenpairs of the matrices derived from the correlations of multichannel observations reflect the cluster structure of the underlying networks. For this we use daily return data from the NYSE and…

Physics and Society · Physics 2009-11-13 Tapio Heimo , Gergely Tibely , Jari Saramaki , Kimmo Kaski , Janos Kertesz

The spectrum of the non-backtracking matrix plays a crucial role in determining various structural and dynamical properties of networked systems, ranging from the threshold in bond percolation and non-recurrent epidemic processes, to…

Physics and Society · Physics 2021-01-11 Romualdo Pastor-Satorras , Claudio Castellano

In high-dimensional principal component analysis, important inferential targets include both leading spikes and the associated principal eigenspaces. Such problems arise naturally in high-dimensional factor models, where leading principal…

Statistics Theory · Mathematics 2026-03-26 Yanqing Yin , Wang Zhou

The largest eigenvalue of a network's adjacency matrix and its associated principal eigenvector are key elements for determining the topological structure and the properties of dynamical processes mediated by it. We present a physically…

Physics and Society · Physics 2017-10-31 Claudio Castellano , Romualdo Pastor-Satorras

This paper examines the relationship between sparse random network architectures and neural network stability by examining the eigenvalue spectral distribution. Specifically, we generalise classical eigenspectral results to sparse…

Neurons and Cognition · Quantitative Biology 2023-10-12 Isabelle D Harris , Hamish Meffin , Anthony N Burkitt , Andre D. H Peterson

Recently, there has been growing evidence that if the width and depth of a neural network are scaled toward the so-called rich feature learning limit (\mup and its depth extension), then some hyperparameters -- such as the learning rate --…

Machine Learning · Computer Science 2024-11-14 Lorenzo Noci , Alexandru Meterez , Thomas Hofmann , Antonio Orvieto

The study of complex networks has been one of the most active fields in science in recent decades. Spectral properties of networks (or graphs that represent them) are of fundamental importance. Researchers have been investigating these…

Combinatorics · Mathematics 2018-09-25 Daniel Montealegre , Van Vu

Although the spectra of random networks have been studied for a long time, the influence of network topology on the dense limit of network spectra remains poorly understood. By considering the configuration model of networks with four…

Disordered Systems and Neural Networks · Physics 2020-10-23 Fernando L. Metz , Jeferson D. Silva

The eigenvalues of matrices representing the structure of large-scale complex networks present a wide range of applications, from the analysis of dynamical processes taking place in the network to spectral techniques aiming to rank the…

Social and Information Networks · Computer Science 2015-03-17 Victor M. Preciado , Ali Jadbabaie

Quantum neural networks hold promise for tackling computationally challenging tasks that are intractable for classical computers. However, their practical application is hindered by significant optimization challenges, arising from complex…

Quantum Physics · Physics 2026-04-23 Yoshiaki Kawase

Covariance and Hessian matrices have been analyzed separately in the literature for classification problems. However, integrating these matrices has the potential to enhance their combined power in improving classification performance. We…

Machine Learning · Computer Science 2024-10-10 Agus Hartoyo , Jan Argasiński , Aleksandra Trenk , Kinga Przybylska , Anna Błasiak , Alessandro Crimi

Many important problems are characterized by the eigenvalues of a large matrix. For example, the difficulty of many optimization problems, such as those arising from the fitting of large models in statistics and machine learning, can be…

We apply state-of-the-art tools in modern high-dimensional numerical linear algebra to approximate efficiently the spectrum of the Hessian of modern deepnets, with tens of millions of parameters, trained on real data. Our results…

Machine Learning · Computer Science 2019-06-04 Vardan Papyan

The distribution of the ratios of consecutive eigenvalue spacings of random matrices has emerged as an important tool to study spectral properties of many-body systems. This article numerically investigates the eigenvalue ratios…

Disordered Systems and Neural Networks · Physics 2022-07-13 Ankit Mishra , Tanu Raghav , Sarika Jalan

Stochastic gradients for deep neural networks exhibit strong correlations along the optimization trajectory, and are often aligned with a small set of Hessian eigenvectors associated with outlier eigenvalues. Recent work shows that…

Machine Learning · Computer Science 2026-02-04 Julien Nicolas , Mohamed Maouche , Sonia Ben Mokhtar , Mark Coates

This paper focuses on obtaining clustering information about a distribution from its i.i.d. samples. We develop theoretical results to understand and use clustering information contained in the eigenvectors of data adjacency matrices based…

Machine Learning · Statistics 2009-11-20 Tao Shi , Mikhail Belkin , Bin Yu

Using the diagrammatic method, we derive a set of self-consistent equations that describe eigenvalue distributions of large correlated asymmetric random matrices. The matrix elements can have different variances and be correlated with each…

Disordered Systems and Neural Networks · Physics 2016-12-21 Alexander Kuczala , Tatyana O. Sharpee

The vibrational behavior of molecules serves as a crucial fingerprint of their structure, chemical state, and surrounding environment. Neutron vibrational spectroscopy provides comprehensive measurements of vibrational modes without…

Chemical Physics · Physics 2025-02-19 Bowen Han , Pei Zhang , Kshitij Mehta , Massimiliano Lupo Pasini , Mingda Li , Yongqiang Cheng