English
Related papers

Related papers: Random Matrix Theory for Deep Learning: Beyond Eig…

200 papers

Learning the manifold structure of remote sensing images is of paramount relevance for modeling and understanding processes, as well as to encapsulate the high dimensionality in a reduced set of informative features for subsequent…

Computer Vision and Pattern Recognition · Computer Science 2022-05-04 Gulsen Taskin , Gustau Camps-Valls

Power systems are developing very fast nowadays, both in size and in complexity; this situation is a challenge for Early Event Detection (EED). This paper proposes a data- driven unsupervised learning method to handle this challenge.…

Methodology · Statistics 2015-09-16 Xing He , Robert Caiming Qiu , Qian Ai , Yinshuang Cao , Jie Gu , Zhijian Jin

The capacity to generalize beyond the range of training data is a pivotal challenge, often synonymous with a model's utility and robustness. This study investigates the comparative abilities of traditional machine learning (ML) models and…

Machine Learning · Computer Science 2024-03-05 Yong Yi Bay , Kathleen A. Yearick

Several variants of recurrent neural networks (RNNs) with orthogonal or unitary recurrent matrices have recently been developed to mitigate the vanishing/exploding gradient problem and to model long-term dependencies of sequences. However,…

Machine Learning · Computer Science 2019-11-20 Kyle Helfrich , Qiang Ye

The landscape of condensed matter physics is facing an unprecedented data surge driven by high-throughput ab initio workflows and rapidly expanding experimental datasets. Traditional first-principles methods such as Density Functional…

Mesoscale and Nanoscale Physics · Physics 2026-04-20 Mahyar Hassani-Vasmejani , Hosein Alavi-Rad , Meysam Bagheri Tagani

In comparison to classical shallow representation learning techniques, deep neural networks have achieved superior performance in nearly every application benchmark. But despite their clear empirical advantages, it is still not well…

Machine Learning · Computer Science 2022-01-11 Calvin Murdock , George Cazenavette , Simon Lucey

The optimal solution to an optimization problem depends on the problem's objective function, constraints, and size. While deep neural networks (DNNs) have proven effective in solving optimization problems, changes in the problem's size,…

Machine Learning · Computer Science 2025-02-17 Nikos A. Mitsiou , Pavlos S. Bouzinis , Panagiotis G. Sarigiannidis , George K. Karagiannidis

In this work, we describe a new approach that uses deep neural networks (DNN) to obtain regularization parameters for solving inverse problems. We consider a supervised learning approach, where a network is trained to approximate the…

Numerical Analysis · Mathematics 2021-04-15 Babak Maboudi Afkham , Julianne Chung , Matthias Chung

Deep Learning (DL), in particular deep neural networks (DNN), by default is purely data-driven and in general does not require physics. This is the strength of DL but also one of its key limitations when applied to science and engineering…

Machine Learning · Statistics 2022-09-26 Hai V. Nguyen , Tan Bui-Thanh

Recurrent neural networks (RNNs) are known to be difficult to train due to the gradient vanishing and exploding problems and thus difficult to learn long-term patterns and construct deep networks. To address these problems, this paper…

Computer Vision and Pattern Recognition · Computer Science 2020-12-10 Shuai Li , Wanqing Li , Chris Cook , Yanbo Gao

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

Deep Reinforcement Learning (RL) powered by neural net approximation of the Q function has had enormous empirical success. While the theory of RL has traditionally focused on linear function approximation (or eluder dimension) approaches,…

Machine Learning · Computer Science 2021-12-28 Baihe Huang , Kaixuan Huang , Sham M. Kakade , Jason D. Lee , Qi Lei , Runzhe Wang , Jiaqi Yang

Empirical observation of high dimensional phenomena, such as the double descent behaviour, has attracted a lot of interest in understanding classical techniques such as kernel methods, and their implications to explain generalization…

In the context of classification problems, Deep Learning (DL) approaches represent state of art. Many DL approaches are based on variations of standard multi-layer feed-forward neural networks. These are also referred to as deep networks.…

Machine Learning · Computer Science 2023-11-21 Andrea Apicella , Francesco Isgrò , Roberto Prevete

We first study the generalization error of models that use a fixed feature representation (frozen intermediate layers) followed by a trainable readout layer. This setting encompasses a range of architectures, from deep random-feature models…

Statistics Theory · Mathematics 2025-11-10 Yessin Moakher , Malik Tiomoko , Cosme Louart , Zhenyu Liao

This paper proposes a new mean-field framework for over-parameterized deep neural networks (DNNs), which can be used to analyze neural network training. In this framework, a DNN is represented by probability measures and functions over its…

Machine Learning · Statistics 2020-07-06 Cong Fang , Jason D. Lee , Pengkun Yang , Tong Zhang

Deep Neural Networks (DNNs) demonstrate remarkable capabilities in learning complex hierarchical data representations, but the nature of these representations remains largely unknown. Existing global explainability methods, such as Network…

Machine Learning · Computer Science 2024-01-19 Kirill Bykov , Laura Kopf , Shinichi Nakajima , Marius Kloft , Marina M. -C. Höhne

Modern deep learning models are highly overparameterized, resulting in large sets of parameter configurations that yield the same outputs. A significant portion of this redundancy is explained by symmetries in the parameter…

Machine Learning · Computer Science 2025-12-12 Bo Zhao , Robin Walters , Rose Yu

One of the most influential results in neural network theory is the universal approximation theorem [1, 2, 3] which states that continuous functions can be approximated to within arbitrary accuracy by single-hidden-layer feedforward neural…

Machine Learning · Computer Science 2021-12-16 Clemens Hutter , Recep Gül , Helmut Bölcskei

Complex nonlinear models such as deep neural network (DNNs) have become an important tool for image classification, speech recognition, natural language processing, and many other fields of application. These models however lack…