English
Related papers

Related papers: Rotate the ReLU to implicitly sparsify deep networ…

200 papers

Activation functions are essential to introduce nonlinearity into neural networks, with the Rectified Linear Unit (ReLU) often favored for its simplicity and effectiveness. Motivated by the structural similarity between a shallow…

Machine Learning · Computer Science 2024-01-30 Jiayun Li , Yuxiao Cheng , Yiwen Lu , Zhuofan Xia , Yilin Mo , Gao Huang

We propose a new notion of `non-linearity' of a network layer with respect to an input batch that is based on its proximity to a linear system, which is reflected in the non-negative rank of the activation matrix. We measure this…

Machine Learning · Computer Science 2018-10-09 Edo Collins , Siavash Arjomand Bigdeli , Sabine Süsstrunk

In this paper, it is demonstrated through a case study that multilayer feedforward neural networks activated by ReLU functions can in principle be trained iteratively with Mixed Integer Linear Programs (MILPs) as follows. Weights are…

Machine Learning · Computer Science 2021-04-12 Steffen Goebbels

We introduce a biologically inspired, multilayer neural architecture composed of Rectified Spectral Units (ReSUs). Each ReSU projects a recent window of its input history onto a canonical direction obtained via canonical correlation…

We prove the first guarantees of sparse recovery for ReLU neural networks, where the sparse network weights constitute the signal to be recovered. Specifically, we study structural properties of the sparse network weights for two-layer,…

Machine Learning · Computer Science 2026-03-03 Sara Fridovich-Keil , Mert Pilanci

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

ReLU neural-networks have been in the focus of many recent theoretical works, trying to explain their empirical success. Nonetheless, there is still a gap between current theoretical results and empirical observations, even in the case of…

Machine Learning · Computer Science 2019-06-13 Jonathan Fiat , Eran Malach , Shai Shalev-Shwartz

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

When optimizing a nonlinear objective, one can employ a neural network as a surrogate for the nonlinear function. However, the resulting optimization model can be time-consuming to solve globally with exact methods. As a result, local…

Optimization and Control · Mathematics 2026-03-19 Jiatai Tong , Yilin Zhu , Thiago Serra , Samuel Burer

Activation function is a pivotal component of deep learning, facilitating the extraction of intricate data patterns. While classical activation functions like ReLU and its variants are extensively utilized, their static nature and…

Machine Learning · Computer Science 2025-11-04 Barathi Subramanian , Rathinaraja Jeyaraj , Rakhmonov Akhrorjon Akhmadjon Ugli

Despite their prevalence in neural networks we still lack a thorough theoretical characterization of ReLU layers. This paper aims to further our understanding of ReLU layers by studying how the activation function ReLU interacts with the…

Machine Learning · Computer Science 2019-08-13 Sören Dittmer , Emily J. King , Peter Maass

Appropriate weight initialization settings, along with the ReLU activation function, have become cornerstones of modern deep learning, enabling the training and deployment of highly effective and efficient neural network models across…

Machine Learning · Computer Science 2024-04-02 Hyunwoo Lee , Yunho Kim , Seung Yeop Yang , Hayoung Choi

ReLU (rectified linear units) neural network has received significant attention since its emergence. In this paper, a univariate ReLU (UReLU) neural network is proposed to both modelling the nonlinear dynamic system and revealing insights…

Systems and Control · Electrical Eng. & Systems 2020-03-06 Xinglong Liang , Jun Xu

This paper presents a unified mixed-integer programming framework for training sparse and interpretable neural networks. We develop exact formulations for both fully connected and convolutional architectures by modeling nonlinearities such…

Artificial Intelligence · Computer Science 2025-04-22 Masoud Ataei , Edrin Hasaj , Jacob Gipp , Sepideh Forouzi

A proper initialization of the weights in a neural network is critical to its convergence. Current insights into weight initialization come primarily from linear activation functions. In this paper, I develop a theory for weight…

Machine Learning · Computer Science 2017-05-04 Siddharth Krishna Kumar

Selecting the most suitable activation function is a critical factor in the effectiveness of deep learning models, as it influences their learning capacity, stability, and computational efficiency. In recent years, the Gaussian Error Linear…

Machine Learning · Computer Science 2023-08-02 Minhyeok Lee

Successfully training deep neural networks often requires either batch normalization, appropriate weight initialization, both of which come with their own challenges. We propose an alternative, geometrically motivated method for training.…

Machine Learning · Computer Science 2019-10-08 Aram-Alexandre Pooladian , Chris Finlay , Adam M Oberman

Neuromorphic hardware tends to pose limits on the connectivity of deep networks that one can run on them. But also generic hardware and software implementations of deep learning run more efficiently for sparse networks. Several methods…

Neural and Evolutionary Computing · Computer Science 2018-08-09 Guillaume Bellec , David Kappel , Wolfgang Maass , Robert Legenstein

We study the role of depth in training randomly initialized overparameterized neural networks. We give a general result showing that depth improves trainability of neural networks by improving the conditioning of certain kernel matrices of…

Machine Learning · Computer Science 2021-02-18 Naman Agarwal , Pranjal Awasthi , Satyen Kale

In this report we demonstrate that with same parameters and computational budgets, models with wider features before ReLU activation have significantly better performance for single image super-resolution (SISR). The resulted SR residual…

Computer Vision and Pattern Recognition · Computer Science 2018-12-24 Jiahui Yu , Yuchen Fan , Jianchao Yang , Ning Xu , Zhaowen Wang , Xinchao Wang , Thomas Huang