English
Related papers

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

200 papers

Loss landscape analysis is extremely useful for a deeper understanding of the generalization ability of deep neural network models. In this work, we propose a layerwise loss landscape analysis where the loss surface at every layer is…

Machine Learning · Computer Science 2020-12-09 Adepu Ravi Sankar , Yash Khasbage , Rahul Vigneswaran , Vineeth N Balasubramanian

We explore the block nature of the matrix representation of multiplex networks, introducing a new formalism to deal with its spectral properties as a function of the inter-layer coupling parameter. This approach allows us to derive…

Physics and Society · Physics 2018-07-17 Guilherme Ferraz de Arruda , Emanuele Cozzo , Francisco A. Rodrigues , Yamir Moreno

Spectral Embedding (SE) has often been used to map data points from non-linear manifolds to linear subspaces for the purpose of classification and clustering. Despite significant advantages, the subspace structure of data in the original…

Computer Vision and Pattern Recognition · Computer Science 2023-05-16 Hira Yaseen , Arif Mahmood

We study how the optimization landscape of a neural network deforms as a non-linear activation is introduced through a smooth homotopy. Working first in an abstract local setting - a smooth one-parameter family of objective functions…

Optimization and Control · Mathematics 2026-04-03 Michael Alexander

We address the amount of information in the non-Gaussian regime of weak lensing surveys by modelling all relevant covariances of the power spectra and bispectra, using 1000 ray-tracing simulation realizations for a Lambda-CDM model and an…

Cosmology and Nongalactic Astrophysics · Physics 2013-08-09 Issha Kayo , Masahiro Takada , Bhuvnesh Jain

Found in varied contexts from neurons to ants to fish, binary decision-making is one of the simplest forms of collective computation. In this process, information collected by individuals about an uncertain environment is accumulated to…

Neurons and Cognition · Quantitative Biology 2019-03-26 Bryan C. Daniels , Pawel Romanczuk

We study Bayesian inference in the spiked covariance model, where a small number of spiked eigenvalues dominate the spectrum. Our goal is to infer the spiked eigenvalues, their corresponding eigenvectors, and the number of spikes, providing…

Statistics Theory · Mathematics 2025-08-20 Kwangmin Lee , Sewon Park , Seongmin Kim , Jaeyong Lee

We present a deep neural network representation of the AdS/CFT correspondence, and demonstrate the emergence of the bulk metric function via the learning process for given data sets of response in boundary quantum field theories. The…

High Energy Physics - Theory · Physics 2018-09-12 Koji Hashimoto , Sotaro Sugishita , Akinori Tanaka , Akio Tomiya

Network representations are useful for describing the structure of a large variety of complex systems. Although most studies of real-world networks suppose that nodes are connected by only a single type of edge, most natural and engineered…

Physics and Society · Physics 2020-08-05 Rubén J. Sánchez-García , Emanuele Cozzo , Yamir Moreno

A Wishart matrix is said to be spiked when the underlying covariance matrix has a single eigenvalue $b$ different from unity. As $b$ increases through $b=2$, a gap forms from the largest eigenvalue to the rest of the spectrum, and with…

Mathematical Physics · Physics 2014-07-01 Peter J. Forrester

This paper is concerned with the interplay between statistical asymmetry and spectral methods. Suppose we are interested in estimating a rank-1 and symmetric matrix $\mathbf{M}^{\star}\in \mathbb{R}^{n\times n}$, yet only a randomly…

Statistics Theory · Mathematics 2023-01-10 Yuxin Chen , Chen Cheng , Jianqing Fan

Real-world large-scale datasets are heteroskedastic and imbalanced -- labels have varying levels of uncertainty and label distributions are long-tailed. Heteroskedasticity and imbalance challenge deep learning algorithms due to the…

Machine Learning · Computer Science 2021-03-19 Kaidi Cao , Yining Chen , Junwei Lu , Nikos Arechiga , Adrien Gaidon , Tengyu Ma

Eigenvalues statistics of various many-body systems have been widely studied using the nearest neighbor spacing distribution under the random matrix theory framework. Here, we numerically analyze eigenvalue ratio statistics of multiplex…

Physics and Society · Physics 2023-05-24 Tanu Raghav , Sarika Jalan

Two ubiquitous aspects of large-scale data analysis are that the data often have heavy-tailed properties and that diffusion-based or spectral-based methods are often used to identify and extract structure of interest. Perhaps surprisingly,…

Machine Learning · Computer Science 2010-05-11 Michael W. Mahoney , Hariharan Narayanan

Kernel spectral clustering corresponds to a weighted kernel principal component analysis problem in a constrained optimization framework. The primal formulation leads to an eigen-decomposition of a centered Laplacian matrix at the dual…

Social and Information Networks · Computer Science 2014-12-03 Raghvendra Mall , Rocco Langone , Johan A. K. Suykens

Spectral clustering is one of the most popular, yet still incompletely understood, methods for community detection on graphs. This article studies spectral clustering based on the Bethe-Hessian matrix $H_r = (r^2-1)I_n + D-rA$ for sparse…

Social and Information Networks · Computer Science 2019-10-10 Lorenzo Dall'Amico , Romain Couillet , Nicolas Tremblay

The eigendecomposition of the coupling matrix of large biological networks is central to the study of the dynamics of these networks. For neural networks, this matrix should reflect the topology of the network and conform with Dale's law…

Neurons and Cognition · Quantitative Biology 2015-09-08 Hervé Rouault , Shaul Druckmann

Higher-order structures of networks, namely, small subgraphs of networks (also called network motifs), are widely known to be crucial and essential to the organization of networks. There has been a few work studying the community detection…

Methodology · Statistics 2023-04-14 Xiao Guo , Hai Zhang , Xiangyu Chang

Doubly-stochastic matrices (DSM) are increasingly utilized in structure-preserving deep architectures -- such as Optimal Transport layers and Sinkhorn-based attention -- to enforce numerical stability and probabilistic interpretability. In…

Machine Learning · Computer Science 2026-01-06 Yizhi Liu

The Diffusion Map is a nonlinear dimensionality reduction technique used to analyze high-dimensional data, with recent applications extending to datasets from the social sciences. Previous research has given little attention to how the…

Physics and Society · Physics 2025-08-28 Sönke Beier
‹ Prev 1 3 4 5 6 7 10 Next ›