English
Related papers

Related papers: Just One Layer Norm Guarantees Stable Extrapolatio…

200 papers

In this paper, we study the generalization performance of overparameterized 3-layer NTK models. We show that, for a specific set of ground-truth functions (which we refer to as the "learnable set"), the test error of the overfitted 3-layer…

Machine Learning · Computer Science 2022-06-07 Peizhong Ju , Xiaojun Lin , Ness B. Shroff

Despite their widespread use, the mechanisms by which large language models (LLMs) represent and regulate uncertainty in next-token predictions remain largely unexplored. This study investigates two critical components believed to influence…

Machine Learning · Computer Science 2024-11-11 Alessandro Stolfo , Ben Wu , Wes Gurnee , Yonatan Belinkov , Xingyi Song , Mrinmaya Sachan , Neel Nanda

An interesting approach to analyzing neural networks that has received renewed attention is to examine the equivalent kernel of the neural network. This is based on the fact that a fully connected feedforward network with one hidden layer,…

Machine Learning · Computer Science 2018-06-04 Russell Tsuchida , Farbod Roosta-Khorasani , Marcus Gallagher

Understanding how neural networks transform input data across layers is fundamental to unraveling their learning and generalization capabilities. Although prior work has used insights from kernel methods to study neural networks, a global…

Machine Learning · Computer Science 2024-10-30 Amir Joudaki , Thomas Hofmann

In this paper, we provide the first precise distributional characterization of gradient descent iterates for general multi-layer neural networks under the canonical single-index regression model, in the `finite-width proportional regime'…

Machine Learning · Computer Science 2025-05-09 Qiyang Han , Masaaki Imaizumi

Spiking neural networks (SNNs) are shown to be more biologically plausible and energy efficient over their predecessors. However, there is a lack of an efficient and generalized training method for deep SNNs, especially for deployment on…

Neural and Evolutionary Computing · Computer Science 2022-10-11 Qu Yang , Jibin Wu , Malu Zhang , Yansong Chua , Xinchao Wang , Haizhou Li

When applying a convolutional kernel to an image, if the output is to remain the same size as the input then some form of padding is required around the image boundary, meaning that for each layer of convolution in a convolutional neural…

Computer Vision and Pattern Recognition · Computer Science 2020-12-07 Calden Wloka , John K. Tsotsos

This work analyzes the training dynamics of Image Restoration (IR) Transformers and uncovers a critical yet overlooked issue: conventional LayerNorm (LN) drives feature magnitudes to diverge to a million scale and collapses channel-wise…

Computer Vision and Pattern Recognition · Computer Science 2026-02-23 MinKyu Lee , Sangeek Hyun , Woojin Jun , Hyunjun Kim , Jiwoo Chung , Jae-Pil Heo

Generalization beyond a training dataset is a main goal of machine learning, but theoretical understanding of generalization remains an open problem for many models. The need for a new theory is exacerbated by recent observations in deep…

Machine Learning · Statistics 2022-02-08 Abdulkadir Canatar , Blake Bordelon , Cengiz Pehlevan

Physics-informed neural networks (PINNs) have lately received great attention thanks to their flexibility in tackling a wide range of forward and inverse problems involving partial differential equations. However, despite their noticeable…

Machine Learning · Computer Science 2020-07-30 Sifan Wang , Xinling Yu , Paris Perdikaris

In Convolutional Neural Network (CNN) based image processing, most of the studies propose networks that are optimized for a single-level (or a single-objective); thus, they underperform on other levels and must be retrained for delivery of…

Computer Vision and Pattern Recognition · Computer Science 2020-03-13 Hyeongmin Lee , Taeoh Kim , Hanbin Son , Sangwook Baek , Minsu Cheon , Sangyoun Lee

We consider shallow (single hidden layer) neural networks and characterize their performance when trained with stochastic gradient descent as the number of hidden units $N$ and gradient descent steps grow to infinity. In particular, we…

Machine Learning · Statistics 2022-06-02 Jiahui Yu , Konstantinos Spiliopoulos

Feature learning is thought to be one of the fundamental reasons for the success of deep neural networks. It is rigorously known that in two-layer fully-connected neural networks under certain conditions, one step of gradient descent on the…

Machine Learning · Statistics 2025-04-11 Behrad Moniri , Donghwan Lee , Hamed Hassani , Edgar Dobriban

We investigate changing the bandwidth of a translational-invariant kernel during training when solving kernel regression with gradient descent. We present a theoretical bound on the out-of-sample generalization error that advocates for…

Machine Learning · Statistics 2025-05-19 Oskar Allerbo

In this paper, we study the data-dependent convergence and generalization behavior of gradient methods for neural networks with smooth activation. Our first result is a novel bound on the excess risk of deep networks trained by the logistic…

Machine Learning · Computer Science 2024-12-09 Hossein Taheri , Christos Thrampoulidis , Arya Mazumdar

The adversarial vulnerability of neural nets, and subsequent techniques to create robust models have attracted significant attention; yet we still lack a full understanding of this phenomenon. Here, we study adversarial examples of trained…

Machine Learning · Computer Science 2023-02-01 Nikolaos Tsilivis , Julia Kempe

Generalization of deep neural networks remains one of the main open problems in machine learning. Previous theoretical works focused on deriving tight bounds of model complexity, while empirical works revealed that neural networks exhibit…

Machine Learning · Computer Science 2022-01-31 James Wang , Cheng-Lin Yang

Deep Convolutional Neural Networks (CNN) enforces supervised information only at the output layer, and hidden layers are trained by back propagating the prediction error from the output layer without explicit supervision. We propose a…

Computer Vision and Pattern Recognition · Computer Science 2016-06-07 Zhuolin Jiang , Yaming Wang , Larry Davis , Walt Andrews , Viktor Rozgic

The performance of the data-dependent neural tangent kernel (NTK; Jacot et al. (2018)) associated with a trained deep neural network (DNN) often matches or exceeds that of the full network. This implies that DNN training via gradient…

Machine Learning · Computer Science 2025-05-22 Johannes Schwab , Bryan Kelly , Semyon Malamud , Teng Andrea Xu

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