English
Related papers

Related papers: Why flatness does and does not correlate with gene…

200 papers

In a recently published paper [1], it is shown that deep neural networks (DNNs) with random Gaussian weights preserve the metric structure of the data, with the property that the distance shrinks more when the angle between the two data…

Machine Learning · Statistics 2019-04-02 Talha Cihad Gulcu , Alper Gungor

Graph neural networks (GNNs) have emerged as a fundamental tool for learning from graph-structured data, achieving strong performance across a wide range of applications. However, understanding their generalization capabilities remains…

Machine Learning · Computer Science 2026-05-14 Peiyao Wang , Liang Bai , Xian Yang , Richard Yi Da Xu , Jiye Liang

Understanding how neural networks generalize on unseen data is crucial for designing more robust and reliable models. In this paper, we study the generalization gap of neural networks using methods from topological data analysis. For this…

Algorithm unfolding or unrolling is the technique of constructing a deep neural network (DNN) from an iterative algorithm. Unrolled DNNs often provide better interpretability and superior empirical performance over standard DNNs in signal…

Machine Learning · Statistics 2024-02-21 Carter Lyons , Raghu G. Raj , Margaret Cheney

We conjecture that the inherent difference in generalisation between adaptive and non-adaptive gradient methods in deep learning stems from the increased estimation noise in the flattest directions of the true loss surface. We demonstrate…

Machine Learning · Statistics 2022-03-17 Diego Granziol , Nicholas Baskerville

We study centralized distributed data parallel training of deep neural networks (DNNs), aiming to improve the trade-off between communication efficiency and model performance of the local gradient methods. To this end, we revisit the…

Machine Learning · Computer Science 2025-10-13 Tolga Dimlioglu , Anna Choromanska

Classical statistical learning theory predicts that overparameterized models should exhibit severe overfitting, yet modern deep neural networks with far more parameters than training samples consistently generalize well. This contradiction…

Machine Learning · Computer Science 2026-04-10 Zeran Johannsen

We analyze the training dynamics for deep linear networks using a new metric - layer imbalance - which defines the flatness of a solution. We demonstrate that different regularization methods, such as weight decay or noise data…

Machine Learning · Computer Science 2020-07-21 Boris Ginsburg

Despite apparent human-level performances of deep neural networks (DNN), they behave fundamentally differently from humans. They easily change predictions when small corruptions such as blur and noise are applied on the input (lack of…

Computer Vision and Pattern Recognition · Computer Science 2020-03-10 Sanghyuk Chun , Seong Joon Oh , Sangdoo Yun , Dongyoon Han , Junsuk Choe , Youngjoon Yoo

Deep neural networks are renowned for their ability to generalise well across diverse tasks, even when heavily overparameterized. Existing works offer only partial explanations (for example, the NTK-based task-model alignment explanation…

Machine Learning · Computer Science 2025-06-02 Chris Mingard , Lukas Seier , Niclas Göring , Andrei-Vlad Badelita , Charles London , Ard Louis

Batch Normalization (BN) has been a standard component in designing deep neural networks (DNNs). Although the standard BN can significantly accelerate the training of DNNs and improve the generalization performance, it has several…

Machine Learning · Computer Science 2020-10-13 Yong Guo , Qingyao Wu , Chaorui Deng , Jian Chen , Mingkui Tan

Recent results in the literature suggest that the penultimate (second-to-last) layer representations of neural networks that are trained for classification exhibit a clustering property called neural collapse (NC). We study the implicit…

Machine Learning · Computer Science 2022-09-29 Tomer Galanti , Liane Galanti , Ido Ben-Shaul

Deep neural networks achieve stellar generalisation on a variety of problems, despite often being large enough to easily fit all their training data. Here we study the generalisation dynamics of two-layer neural networks in a…

Machine Learning · Statistics 2019-06-21 Sebastian Goldt , Madhu S. Advani , Andrew M. Saxe , Florent Krzakala , Lenka Zdeborová

This paper proposes a new optimization algorithm called Entropy-SGD for training deep neural networks that is motivated by the local geometry of the energy landscape. Local extrema with low generalization error have a large proportion of…

Bounding and predicting the generalization gap of overparameterized neural networks remains a central open problem in theoretical machine learning. There is a recent and growing body of literature that proposes the framework of fractals to…

Machine Learning · Computer Science 2024-11-04 Charlie B. Tan , Inés García-Redondo , Qiquan Wang , Michael M. Bronstein , Anthea Monod

With a goal of understanding what drives generalization in deep networks, we consider several recently suggested explanations, including norm-based control, sharpness and robustness. We study how these measures can ensure generalization,…

Machine Learning · Computer Science 2017-07-07 Behnam Neyshabur , Srinadh Bhojanapalli , David McAllester , Nathan Srebro

Deep neural networks (DNNs) have demonstrated dominating performance in many fields; since AlexNet, networks used in practice are going wider and deeper. On the theoretical side, a long line of works has been focusing on training neural…

Machine Learning · Computer Science 2019-06-18 Zeyuan Allen-Zhu , Yuanzhi Li , Zhao Song

Stochastic gradient descent (SGD) is widely used in machine learning. Although being commonly viewed as a fast but not accurate version of gradient descent (GD), it always finds better solutions than GD for modern neural networks. In order…

Machine Learning · Computer Science 2018-08-17 Robert Kleinberg , Yuanzhi Li , Yang Yuan

While deep learning is successful in a number of applications, it is not yet well understood theoretically. A satisfactory theoretical characterization of deep learning however, is beginning to emerge. It covers the following questions: 1)…

Machine Learning · Computer Science 2019-08-27 Tomaso Poggio , Andrzej Banburski , Qianli Liao

Quantifying the complexity of feed-forward neural networks (FFNNs) remains challenging due to their nonlinear, hierarchical structure and numerous parameters. We apply generalized degrees of freedom (GDF) to measure model complexity in…

Methodology · Statistics 2026-02-17 Jia Zhou , Douglas Landsittel