English
Related papers

Related papers: Stiffness: A New Perspective on Generalization in …

200 papers

Modern deep neural network training is typically based on mini-batch stochastic gradient optimization. While the use of large mini-batches increases the available computational parallelism, small batch training has been shown to provide…

Machine Learning · Computer Science 2018-04-23 Dominic Masters , Carlo Luschi

We propose to impose symmetry in neural network parameters to improve parameter usage and make use of dedicated convolution and matrix multiplication routines. Due to significant reduction in the number of parameters as a result of the…

Machine Learning · Computer Science 2019-01-11 Xu Shell Hu , Sergey Zagoruyko , Nikos Komodakis

The presence of mislabeled observations in data is a notoriously challenging problem in statistics and machine learning, associated with poor generalization properties for both traditional classifiers and, perhaps even more so, flexible…

Machine Learning · Statistics 2022-02-09 Olof Zetterqvist , Rebecka Jörnsten , Johan Jonasson

We investigate the generalization and optimization properties of shallow neural-network classifiers trained by gradient descent in the interpolating regime. Specifically, in a realizable scenario where model weights can achieve arbitrarily…

Machine Learning · Statistics 2023-03-29 Hossein Taheri , Christos Thrampoulidis

Grokking refers to delayed generalization in which the increase in test accuracy of a neural network occurs appreciably after the improvement in training accuracy This paper introduces several practical metrics including variance under…

Machine Learning · Computer Science 2025-07-17 Ahmed Salah , David Yevick

This paper presents an experimental study focused on understanding the simplification properties of neural networks under different hyperparameter configurations, specifically investigating the effects on Lempel Ziv complexity and…

Machine Learning · Computer Science 2024-09-25 Huixin Guan

As deep neural networks (DNNs) achieve tremendous success across many application domains, researchers tried to explore in many aspects on why they generalize well. In this paper, we provide a novel perspective on these issues using the…

Machine Learning · Computer Science 2020-02-25 Jinlong Liu , Guoqing Jiang , Yunzhi Bai , Ting Chen , Huayan Wang

Along with the rapid development of deep learning in practice, the theoretical explanations for its success become urgent. Generalization and expressivity are two widely used measurements to quantify theoretical behaviors of deep learning.…

Machine Learning · Computer Science 2018-03-26 Shao-Bo Lin

This work describes how the formalization of complex network concepts in terms of discrete mathematics, especially mathematical morphology, allows a series of generalizations and important results ranging from new measurements of the…

Statistical Mechanics · Physics 2007-09-19 Luciano da Fontoura Costa , Luis Enrique C. da Rocha

This paper investigates how various randomization techniques impact Deep Neural Networks (DNNs). Randomization, like weight noise and dropout, aids in reducing overfitting and enhancing generalization, but their interactions are poorly…

Recent works have highlighted scale invariance or symmetry present in the weight space of a typical deep network and the adverse effect it has on the Euclidean gradient based stochastic gradient descent optimization. In this work, we show…

Machine Learning · Computer Science 2015-11-04 Vijay Badrinarayanan , Bamdev Mishra , Roberto Cipolla

Neural networks are nowadays highly successful despite strong hardness results. The existing hardness results focus on the network architecture, and assume that the network's weights are arbitrary. A natural approach to settle the…

Machine Learning · Computer Science 2020-10-15 Amit Daniely , Gal Vardi

In this paper we propose a method of obtaining points of extreme overfitting - parameters of modern neural networks, at which they demonstrate close to 100 % training accuracy, simultaneously with almost zero accuracy on the test sample.…

Machine Learning · Computer Science 2020-04-03 Daniil Merkulov , Ivan Oseledets

Neural Collapse refers to the curious phenomenon in the end of training of a neural network, where feature vectors and classification weights converge to a very simple geometrical arrangement (a simplex). While it has been observed…

Machine Learning · Computer Science 2024-11-14 Jingtong Su , Ya Shi Zhang , Nikolaos Tsilivis , Julia Kempe

Many algorithms and observed phenomena in deep learning appear to be affected by parameter symmetries -- transformations of neural network parameters that do not change the underlying neural network function. These include linear mode…

Machine Learning · Computer Science 2024-10-16 Derek Lim , Theo Moe Putterman , Robin Walters , Haggai Maron , Stefanie Jegelka

Deep classifier neural networks enter the terminal phase of training (TPT) when training error reaches zero and tend to exhibit intriguing Neural Collapse (NC) properties. Neural collapse essentially represents a state at which the…

Machine Learning · Computer Science 2023-04-12 Vignesh Kothapalli

It has been observed in practice that applying pruning-at-initialization methods to neural networks and training the sparsified networks can not only retain the testing performance of the original dense models, but also sometimes even…

Machine Learning · Computer Science 2023-01-31 Hongru Yang , Yingbin Liang , Xiaojie Guo , Lingfei Wu , Zhangyang Wang

Network analysis is an important tool in understanding the behavior of complex systems of interacting entities. However, due to the limitations of data gathering technologies, some interactions might be missing from the network model. This…

Social and Information Networks · Computer Science 2016-08-25 Soumya Sarkar , Sanjukta Bhowmick , Suhansanu Kumar , Animesh Mukherjee

In recent years, continual learning, a prediction setting in which the problem environment may evolve over time, has become an increasingly popular research field due to the framework's gearing towards complex, non-stationary objectives.…

Machine Learning · Computer Science 2024-09-27 Max Koster , Jude Kukla

We analyze recurrent neural networks with diagonal hidden-to-hidden weight matrices, trained with gradient descent in the supervised learning setting, and prove that gradient descent can achieve optimality \emph{without} massive…

Machine Learning · Computer Science 2024-10-11 Semih Cayci , Atilla Eryilmaz