English
Related papers

Related papers: Most ReLU Networks Admit Identifiable Parameters

200 papers

In this paper, we investigate the relationship between deep neural networks (DNN) with rectified linear unit (ReLU) function as the activation function and continuous piecewise linear (CPWL) functions, especially CPWL functions from the…

Numerical Analysis · Mathematics 2020-06-02 Juncai He , Lin Li , Jinchao Xu , Chunyue Zheng

Neural networks have shown high successful performance in a wide range of tasks, but further studies are needed to improve its performance. We analyze the approximation error of the specific neural network architecture with a local…

Machine Learning · Computer Science 2020-09-04 Jae-Mo Kang , Sunghwan Moon

Deep neural networks (DNNs), particularly those using Rectified Linear Unit (ReLU) activation functions, have achieved remarkable success across diverse machine learning tasks, including image recognition, audio processing, and language…

Machine Learning · Computer Science 2026-03-26 Emi Zeger , Mert Pilanci

The implicit bias induced by the training of neural networks has become a topic of rigorous study. In the limit of gradient flow and gradient descent with appropriate step size, it has been shown that when one trains a deep linear network…

Machine Learning · Computer Science 2022-04-27 Thien Le , Stefanie Jegelka

We consider functions from the real numbers to the real numbers, output by a neural network with 1 hidden activation layer, arbitrary width, and ReLU activation function. We assume that the parameters of the neural network are chosen…

Machine Learning · Computer Science 2023-04-20 David Holmes

Understanding implicit bias of gradient descent for generalization capability of ReLU networks has been an important research topic in machine learning research. Unfortunately, even for a single ReLU neuron trained with the square loss, it…

Machine Learning · Computer Science 2022-06-14 Sangmin Lee , Byeongsu Sim , Jong Chul Ye

Recent works show that overparameterized networks contain small subnetworks that exhibit comparable accuracy to the full model when trained in isolation. These results highlight the potential to reduce training costs of deep neural networks…

Machine Learning · Computer Science 2020-06-25 Roger Waleffe , Theodoros Rekatsinas

Deep neural networks come in many sizes and architectures. The choice of architecture, in conjunction with the dataset and learning algorithm, is commonly understood to affect the learned neural representations. Yet, recent results have…

Machine Learning · Computer Science 2024-07-08 Loek van Rossem , Andrew M. Saxe

In this paper, we investigate the Rademacher complexity of deep sparse neural networks, where each neuron receives a small number of inputs. We prove generalization bounds for multilayered sparse ReLU neural networks, including…

Machine Learning · Computer Science 2023-01-31 Tomer Galanti , Mengjia Xu , Liane Galanti , Tomaso Poggio

Understanding the fundamental mechanism behind the success of deep neural networks is one of the key challenges in the modern machine learning literature. Despite numerous attempts, a solid theoretical analysis is yet to be developed. In…

Machine Learning · Computer Science 2022-01-14 Tolga Ergen , Mert Pilanci

This article concerns the expressive power of depth in neural nets with ReLU activations and bounded width. We are particularly interested in the following questions: what is the minimal width $w_{\text{min}}(d)$ so that ReLU nets of width…

Machine Learning · Statistics 2019-10-22 Boris Hanin

This paper establishes the (nearly) optimal approximation error characterization of deep rectified linear unit (ReLU) networks for smooth functions in terms of both width and depth simultaneously. To that end, we first prove that…

Machine Learning · Computer Science 2021-11-03 Jianfeng Lu , Zuowei Shen , Haizhao Yang , Shijun Zhang

We consider the phenomenon of adversarial examples in ReLU networks with independent gaussian parameters. For networks of constant depth and with a large range of widths (for instance, it suffices if the width of each layer is polynomial in…

Machine Learning · Computer Science 2021-06-25 Peter L. Bartlett , Sébastien Bubeck , Yeshwanth Cherapanamjeri

Deep learning is recognized to be capable of discovering deep features for representation learning and pattern recognition without requiring elegant feature engineering techniques by taking advantage of human ingenuity and prior knowledge.…

Machine Learning · Computer Science 2020-04-02 Zhi Han , Siquan Yu , Shao-Bo Lin , Ding-Xuan Zhou

In this paper, we consider one dimensional (shallow) ReLU neural networks in which weights are chosen randomly and only the terminal layer is trained. First, we mathematically show that for such networks L2-regularized regression…

Machine Learning · Computer Science 2023-10-05 Jakob Heiss , Josef Teichmann , Hanna Wutte

The topology of many real complex networks has been conjectured to be embedded in hidden metric spaces, where distances between nodes encode their likelihood of being connected. Besides of providing a natural geometrical interpretation of…

Physics and Society · Physics 2017-01-23 Antoine Allard , M. Ángeles Serrano , Guillermo García-Pérez , Marián Boguñá

In the recent literature the important role of depth in deep learning has been emphasized. In this paper we argue that sufficient width of a feedforward network is equally important by answering the simple question under which conditions…

Machine Learning · Computer Science 2018-06-11 Quynh Nguyen , Mahesh Chandra Mukkamala , Matthias Hein

We describe an algorithm that learns two-layer residual units using rectified linear unit (ReLU) activation: suppose the input $\mathbf{x}$ is from a distribution with support space $\mathbb{R}^d$ and the ground-truth generative model is a…

Machine Learning · Computer Science 2022-12-13 Zhunxuan Wang , Linyun He , Chunchuan Lyu , Shay B. Cohen

Previous work has shown that a neural network with the rectified linear unit (ReLU) activation function leads to a convex polyhedral decomposition of the input space. These decompositions can be represented by a dual graph with vertices…

Computer Vision and Pattern Recognition · Computer Science 2022-12-06 Huma Jamil , Yajing Liu , Christina M. Cole , Nathaniel Blanchard , Emily J. King , Michael Kirby , Christopher Peterson

To better understand complexity in neural networks, we theoretically investigate the idealised phenomenon of lossless network compressibility, whereby an identical function can be implemented with fewer hidden units. In the setting of…

Machine Learning · Computer Science 2024-05-27 Matthew Farrugia-Roberts