English
Related papers

Related papers: Subaging in underparametrized Deep Neural Networks

200 papers

Our theoretical understanding of deep learning has not kept pace with its empirical success. While network architecture is known to be critical, we do not yet understand its effect on learned representations and network behavior, or how…

Machine Learning · Computer Science 2022-07-22 Andrew M. Saxe , Shagun Sodhani , Sam Lewallen

Deep neural networks with remarkably strong generalization performances are usually over-parameterized. Despite explicit regularization strategies are used for practitioners to avoid over-fitting, the impacts are often small. Some…

Computation and Language · Computer Science 2018-11-05 Deren Lei , Zichen Sun , Yijun Xiao , William Yang Wang

This study focuses on the task of supervised prediction of aging-related genes from -omics data. Unlike gene expression methods for this task that capture aging-specific information but ignore interactions between genes (i.e., their protein…

Molecular Networks · Quantitative Biology 2021-04-14 Qi Li , Khalique Newaz , Tijana Milenković

The subject of study is a neural network with binary neurons, randomly diluted synapses and variable pattern activity. We look at the system with parallel updating using a probabilistic approach to solve the one step dynamics with one…

Disordered Systems and Neural Networks · Physics 2009-10-31 Stefan Grosskinsky

Deep neural networks have reshaped modern machine learning by learning powerful latent representations that often align with the manifold hypothesis: high-dimensional data lie on lower-dimensional manifolds. In this paper, we establish a…

Machine Learning · Computer Science 2025-06-09 Nico Pelleriti , Max Zimmer , Elias Wirth , Sebastian Pokutta

Entropic aging consists in a progressive slowing down of the low-temperature dynamics of a glassy system due to the rarefaction of downwards directions on the energy landscape, as lower and lower energy levels are reached. A prototypical…

Statistical Mechanics · Physics 2010-07-23 Eric Bertin

Although species longevity is subject to a diverse range of selective forces, the mortality curves of a wide variety of organisms are rather similar. We argue that aging and its universal characteristics may have evolved by means of a…

Populations and Evolution · Quantitative Biology 2013-02-01 Dervis Can Vural , Greg Morrison , L. Mahadevan

We investigate the aging behavior of lattice-gas models with constrained dynamics in which particle exchange with a reservoir is allowed. Such models provide a particularly simple interpretation of aging phenomena as a slow approach to…

Statistical Mechanics · Physics 2009-10-30 Jorge Kurchan , Luca Peliti , Mauro Sellitto

Overparameterization, the condition where models have more parameters than necessary to fit their training loss, is a crucial factor for the success of deep learning. However, the characteristics of the features learned by overparameterized…

Machine Learning · Computer Science 2024-07-02 Ahmet Cagri Duzgun , Samy Jelassi , Yuanzhi Li

Deep learning models' architectures, including depth and width, are key factors influencing models' performance, such as test accuracy and computation time. This paper solves two problems: given computation time budget, choose an…

Machine Learning · Statistics 2018-02-22 Junqi Jin , Ziang Yan , Kun Fu , Nan Jiang , Changshui Zhang

Recently we have used a cellular automata model which describes the dynamics of a multi-connected network to reproduce the refractory behavior and aging effects obtained in immunization experiments performed with mice when subjected to…

Statistical Mechanics · Physics 2007-05-23 Mauro Copelli , Rita M. Zorzenon dos Santos , Daniel A. Stariolo

Despite the widespread adoption of neural networks, their training dynamics remain poorly understood. We show experimentally that as the size of the dataset increases, a point forms where the magnitude of the gradient of the loss becomes…

Machine Learning · Computer Science 2024-07-23 Mark Lowell

A main puzzle of deep networks revolves around the absence of overfitting despite large overparametrization and despite the large capacity demonstrated by zero training error on randomly labeled data. In this note, we show that the dynamics…

Assisted by the availability of data and high performance computing, deep learning techniques have achieved breakthroughs and surpassed human performance empirically in difficult tasks, including object recognition, speech recognition, and…

Machine Learning · Computer Science 2019-01-23 Shaeke Salman , Xiuwen Liu

As the aging population grows, particularly for the baby boomer generation, the United States is witnessing a significant increase in the elderly population experiencing multifunctional disabilities. These disabilities, stemming from a…

Machine Learning · Computer Science 2024-04-09 Suiyao Chen , Xinyi Liu , Yulei Li , Jing Wu , Handong Yao

Recently, over-parameterized neural networks have been extensively analyzed in the literature. However, the previous studies cannot satisfactorily explain why fully trained neural networks are successful in practice. In this paper, we…

Machine Learning · Computer Science 2019-10-28 Cong Fang , Hanze Dong , Tong Zhang

We explore some mathematical features of the loss landscape of overparameterized neural networks. A priori one might imagine that the loss function looks like a typical function from $\mathbb{R}^n$ to $\mathbb{R}$ - in particular,…

Machine Learning · Computer Science 2018-04-27 Y Cooper

We investigate aging in glassy systems based on a simple model, where a point in configuration space performs thermally activated jumps between the minima of a random energy landscape. The model allows us to show explicitly a subaging…

Statistical Mechanics · Physics 2009-10-31 Bernd Rinn , Philipp Maass , Jean-Philippe Bouchaud

Dropout regularization of deep neural networks has been a mysterious yet effective tool to prevent overfitting. Explanations for its success range from the prevention of "co-adapted" weights to it being a form of cheap Bayesian inference.…

Machine Learning · Statistics 2019-05-30 Eric Nalisnick , José Miguel Hernández-Lobato , Padhraic Smyth

Complex nonlinear dynamics are ubiquitous in many fields. Moreover, we rarely have access to all of the relevant state variables governing the dynamics. Delay embedding allows us, in principle, to account for unobserved state variables.…

Machine Learning · Computer Science 2022-04-27 Uttam Bhat , Stephan B. Munch