English
Related papers

Related papers: Subaging in underparametrized Deep Neural Networks

200 papers

Deep Neural Networks (DNNs) have been successfully applied to a wide range of problems. However, two main limitations are commonly pointed out. The first one is that they require long time to design. The other is that they heavily rely on…

Neural and Evolutionary Computing · Computer Science 2024-06-21 Adriano Vinhas , João Correia , Penousal Machado

The representation of functions by artificial neural networks depends on a large number of parameters in a non-linear fashion. Suitable parameters of these are found by minimizing a 'loss functional', typically by stochastic gradient…

Machine Learning · Computer Science 2021-09-16 Stephan Wojtowytsch

Distribution network reconfiguration (DNR) is a tool used by operators to balance line load flows and mitigate losses. As distributed generation and flexible load adoption increases, the impact of DNR on the security, efficiency, and…

Deep continual learning requires models to adapt to new tasks without retraining from scratch. However, neural networks can lose their ability to adapt to new tasks after training on previous ones, a phenomenon known as loss of plasticity.…

Machine Learning · Computer Science 2026-05-12 Jiuqi Wang , Jayanth Srinivasa , Claire Chen , Shuze Daniel Liu , Ali Payani , Shangtong Zhang

We theoretically characterize gradient descent dynamics in deep linear networks trained at large width from random initialization and on large quantities of random data. Our theory captures the ``wider is better" effect of…

Machine Learning · Computer Science 2025-06-17 Blake Bordelon , Cengiz Pehlevan

Training deep neural networks for classification often includes minimizing the training loss beyond the zero training error point. In this phase of training, a "neural collapse" behavior has been observed: the variability of features…

Machine Learning · Computer Science 2023-05-30 Tom Tirer , Haoxiang Huang , Jonathan Niles-Weed

Cognition in midlife is an important predictor of age-related mental decline and statistical models that predict cognitive performance can be useful for predicting decline. However, existing models struggle to capture complex relationships…

Machine Learning · Computer Science 2021-12-30 Sharath Koorathota , Arunesh Mittal , Richard P. Sloan , Paul Sajda

A promising approach to improve climate-model simulations is to replace traditional subgrid parameterizations based on simplified physical models by machine learning algorithms that are data-driven. However, neural networks (NNs) often lead…

Atmospheric and Oceanic Physics · Physics 2021-04-07 Janni Yuval , Paul A. O'Gorman , Chris N. Hill

Deep neural networks are among the most widely applied machine learning tools showing outstanding performance in a broad range of tasks. We present a method for folding a deep neural network of arbitrary size into a single neuron with…

Machine Learning · Computer Science 2021-09-15 Florian Stelzer , André Röhm , Raul Vicente , Ingo Fischer , Serhiy Yanchuk

In this theory paper, we investigate training deep neural networks (DNNs) for classification via minimizing the information bottleneck (IB) functional. We show that the resulting optimization problem suffers from two severe issues: First,…

Machine Learning · Computer Science 2020-08-10 Rana Ali Amjad , Bernhard C. Geiger

Dynamical systems are often time-varying, whose modeling requires a function that evolves with respect to time. Recent studies such as the neural ordinary differential equation proposed a time-dependent neural network, which provides a…

Machine Learning · Computer Science 2024-05-24 Bum Jun Kim , Yoshinobu Kawahara , Sang Woo Kim

We observe non-monotonic aging and memory effects, two hallmarks of glassy dynamics, in two disordered mechanical systems: crumpled thin sheets and elastic foams. Under fixed compression, both systems exhibit monotonic non-exponential…

Soft Condensed Matter · Physics 2017-04-14 Yoav Lahini , Omer Gottesman , Ariel Amir , Shmuel M. Rubinstein

Why do deep networks generalize well? In contrast to classical generalization theory, we approach this fundamental question by examining not only inputs and outputs, but the evolution of internal features. Our study suggests a phenomenon of…

Machine Learning · Computer Science 2025-10-06 Tianyu Ruan , Kuo Gai , Shihua Zhang

We develop a Mean-Field (MF) view of the learning dynamics of overparametrized Artificial Neural Networks (NN) under data symmetric in law wrt the action of a general compact group $G$. We consider for this a class of generalized shallow…

Machine Learning · Statistics 2025-05-27 Javier Maass , Joaquin Fontbona

Deep neural networks are able to solve tasks across a variety of domains and modalities of data. Despite many empirical successes, we lack the ability to clearly understand and interpret the learned internal mechanisms that contribute to…

Artificial Intelligence · Computer Science 2018-01-03 Christopher Grimm , Dilip Arumugam , Siddharth Karamcheti , David Abel , Lawson L. S. Wong , Michael L. Littman

The impressive success of modern deep neural networks on computer vision tasks has been achieved through models of very large capacity compared to the number of available training examples. This overparameterization is often said to be…

Computer Vision and Pattern Recognition · Computer Science 2018-07-13 Alex Hernández-García , Peter König

Optimizing a neural network's performance is a tedious and time taking process, this iterative process does not have any defined solution which can work for all the problems. Optimization can be roughly categorized into - Architecture and…

Machine Learning · Computer Science 2019-12-16 Siddhartha Dhar Choudhury , Shashank Pandey , Kunal Mehrotra

This paper considers deep neural networks for learning weakly dependent processes in a general framework that includes, for instance, regression estimation, time series prediction, time series classification. The $\psi$-weak dependence…

Machine Learning · Statistics 2023-02-16 William Kengne

In this work, we investigate a particular implicit bias in gradient descent training, which we term "Feature Averaging," and argue that it is one of the principal factors contributing to the non-robustness of deep neural networks. We show…

Machine Learning · Computer Science 2025-03-04 Binghui Li , Zhixuan Pan , Kaifeng Lyu , Jian Li

Deep neural networks generalize well despite being exceedingly overparameterized and being trained without explicit regularization. This curious phenomenon has inspired extensive research activity in establishing its statistical principles:…

Machine Learning · Statistics 2021-09-16 Ke Wang , Christos Thrampoulidis