English
Related papers

Related papers: Efficient Algorithms for Learning Depth-2 Neural N…

200 papers

The choice of activation functions in deep networks has a significant effect on the training dynamics and task performance. Currently, the most successful and widely-used activation function is the Rectified Linear Unit (ReLU). Although…

Neural and Evolutionary Computing · Computer Science 2017-10-30 Prajit Ramachandran , Barret Zoph , Quoc V. Le

This paper presents an investigation of the approximation property of neural networks with unbounded activation functions, such as the rectified linear unit (ReLU), which is the new de-facto standard of deep learning. The ReLU network can…

Neural and Evolutionary Computing · Computer Science 2019-02-27 Sho Sonoda , Noboru Murata

The implicit bias towards solutions with favorable properties is believed to be a key reason why neural networks trained by gradient-based optimization can generalize well. While the implicit bias of gradient flow has been widely studied…

Machine Learning · Computer Science 2023-10-31 Yiwen Kou , Zixiang Chen , Quanquan Gu

Neural networks are usually trained with different variants of gradient descent based optimization algorithms such as stochastic gradient descent or the Adam optimizer. Recent theoretical work states that the critical points (where the…

Machine Learning · Computer Science 2024-10-15 Adrian Barbu

In the last decade, an active area of research has been devoted to design novel activation functions that are able to help deep neural networks to converge, obtaining better performance. The training procedure of these architectures usually…

Machine Learning · Computer Science 2019-04-26 Franco Manessi , Alessandro Rozza

This paper aims to understand the training solution, which is obtained by the back-propagation algorithm, of two-layer neural networks whose hidden layer is composed of the units with smooth activation functions, including the usual sigmoid…

Machine Learning · Computer Science 2025-07-22 Changcun Huang

The training process of neural networks usually optimize weights and bias parameters of linear transformations, while nonlinear activation functions are pre-specified and fixed. This work develops a systematic approach to constructing…

Machine Learning · Computer Science 2024-10-29 Zhengqi Liu , Shuhao Cao , Yuwen Li , Ludmil Zikatanov

We prove a large deviation principle for deep neural networks with Gaussian weights and at most linearly growing activation functions, such as ReLU. This generalises earlier work, in which bounded and continuous activation functions were…

Machine Learning · Statistics 2026-02-10 Quirin Vogel

We analyze the convergence of (stochastic) gradient descent algorithm for learning a convolutional filter with Rectified Linear Unit (ReLU) activation function. Our analysis does not rely on any specific form of the input distribution and…

Machine Learning · Computer Science 2018-03-01 Simon S. Du , Jason D. Lee , Yuandong Tian

We investigate the implications of removing bias in ReLU networks regarding their expressivity and learning dynamics. We first show that two-layer bias-free ReLU networks have limited expressivity: the only odd function two-layer bias-free…

Machine Learning · Computer Science 2025-04-29 Yedi Zhang , Andrew Saxe , Peter E. Latham

We give the first provably efficient algorithms for learning neural networks with distribution shift. We work in the Testable Learning with Distribution Shift framework (TDS learning) of Klivans et al. (2024), where the learner receives…

Data Structures and Algorithms · Computer Science 2025-02-25 Gautam Chandrasekaran , Adam R. Klivans , Lin Lin Lee , Konstantinos Stavropoulos

Researchers have proposed various activation functions. These activation functions help the deep network to learn non-linear behavior with a significant effect on training dynamics and task performance. The performance of these activations…

Computer Vision and Pattern Recognition · Computer Science 2020-01-07 Pravendra Singh , Munender Varshney , Vinay P. Namboodiri

In deep learning, a central issue is to understand how neural networks efficiently learn high-dimensional features. To this end, we explore the gradient descent learning of a general Gaussian Multi-index model…

Machine Learning · Statistics 2026-02-06 Bohan Zhang , Zihao Wang , Hengyu Fu , Jason D. Lee

Consider the multivariate nonparametric regression model. It is shown that estimators based on sparsely connected deep neural networks with ReLU activation function and properly chosen network architecture achieve the minimax rates of…

Statistics Theory · Mathematics 2020-09-15 Johannes Schmidt-Hieber

Rectified linear activation units are important components for state-of-the-art deep convolutional networks. In this paper, we propose a novel S-shaped rectified linear activation unit (SReLU) to learn both convex and non-convex functions,…

Computer Vision and Pattern Recognition · Computer Science 2015-12-23 Xiaojie Jin , Chunyan Xu , Jiashi Feng , Yunchao Wei , Junjun Xiong , Shuicheng Yan

This paper explores the topological signatures of ReLU neural network activation patterns. We consider feedforward neural networks with ReLU activation functions and analyze the polytope decomposition of the feature space induced by the…

Machine Learning · Computer Science 2026-04-20 Vicente Bosca , Tatum Rask , Sunia Tanweer , Andrew R. Tawfeek , Branden Stone

The success of deep networks has been attributed in part to their expressivity: per parameter, deep networks can approximate a richer class of functions than shallow networks. In ReLU networks, the number of activation patterns is one…

Machine Learning · Statistics 2019-10-22 Boris Hanin , David Rolnick

We give a polynomial-time algorithm for learning neural networks with one layer of sigmoids feeding into any Lipschitz, monotone activation function (e.g., sigmoid or ReLU). We make no assumptions on the structure of the network, and the…

Data Structures and Algorithms · Computer Science 2018-04-24 Surbhi Goel , Adam Klivans

We establish connections between the problem of learning a two-layer neural network and tensor decomposition. We consider a model with feature vectors $\boldsymbol x \in \mathbb R^d$, $r$ hidden units with weights $\{\boldsymbol w_i\}_{1\le…

Machine Learning · Computer Science 2018-10-11 Marco Mondelli , Andrea Montanari

Active learning methods aim to improve sample complexity in machine learning. In this work, we investigate an active learning scheme via a novel gradient-free cutting-plane training method for ReLU networks of arbitrary depth and develop a…

Machine Learning · Computer Science 2025-06-26 Erica Zhang , Fangzhao Zhang , Mert Pilanci