English
Related papers

Related papers: Bug or Feature$^2$: Weight Drift, Activation Spars…

200 papers

Activation functions are essential to deep learning networks. Popular and versatile activation functions are mostly monotonic functions, some non-monotonic activation functions are being explored and show promising performance. But by…

Neural and Evolutionary Computing · Computer Science 2023-05-26 Junjia Chen , Zhibin Pan

Structured sparsity accelerates training and inference on modern GPUs, yet it still trails unstructured dynamic sparse training (DST) in accuracy. The shortfall stems from a loss of expressivity: whereas a dense layer can realize every…

Machine Learning · Computer Science 2025-10-17 Abhishek Tyagi , Arjun Iyer , Liam Young , William H Renninger , Christopher Kanan , Yuhao Zhu

Leveraging sparsity is crucial for optimizing large language model inference. however, modern LLMs employing SiLU as their activation function exhibit minimal activation sparsity. Recent research has proposed replacing SiLU with ReLU to…

Performance · Computer Science 2025-01-27 Jiho Shin , Hoeseok Yang , Youngmin Yi

Activation functions have come up as one of the essential components of neural networks. The choice of adequate activation function can impact the accuracy of these methods. In this study, we experiment for finding an optimal activation…

Machine Learning · Computer Science 2022-02-25 Vipul Bansal

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

Despite the empirical success of using Adversarial Training to defend deep learning models against adversarial perturbations, so far, it still remains rather unclear what the principles are behind the existence of adversarial perturbations,…

Machine Learning · Computer Science 2022-06-14 Zeyuan Allen-Zhu , Yuanzhi Li

It is well-known that overparametrized neural networks trained using gradient-based methods quickly achieve small training error with appropriate hyperparameter settings. Recent papers have proved this statement theoretically for highly…

Machine Learning · Computer Science 2020-04-13 Abhishek Panigrahi , Abhishek Shetty , Navin Goyal

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 study the least-square regression problem with a two-layer fully-connected neural network, with ReLU activation function, trained by gradient flow. Our first result is a generalization result, that requires no assumptions on the…

Machine Learning · Computer Science 2024-10-10 Junhyung Park , Patrick Bloebaum , Shiva Prasad Kasiviswanathan

Large Language Models (LLMs) have achieved remarkable capabilities, but their immense computational demands during training remain a critical bottleneck for widespread adoption. Low-rank training has received attention in recent years due…

Machine Learning · Computer Science 2026-05-06 Jiaxi Li , Lu Yin , Li Shen , Jinjin Xu , Yuhui Liu , Wenwu Wang , Shiwei Liu , Xilu Wang

Neural networks are trained by choosing an architecture and training the parameters. The choice of architecture is often by trial and error or with Neural Architecture Search (NAS) methods. While NAS provides some automation, it often…

Machine Learning · Computer Science 2024-10-14 Zitong Huang , Mansooreh Montazerin , Ajitesh Srivastava

We consider the problem of finding a two-layer neural network with sigmoid, rectified linear unit (ReLU), or binary step activation functions that "fits" a training data set as accurately as possible as quantified by the training error; and…

Machine Learning · Statistics 2022-04-06 David Gamarnik , Eren C. Kızıldağ , Ilias Zadik

Gradient descent (GD) type optimization schemes are the standard methods to train artificial neural networks (ANNs) with rectified linear unit (ReLU) activation. Such schemes can be considered as discretizations of gradient flows (GFs)…

Machine Learning · Computer Science 2022-09-27 Arnulf Jentzen , Adrian Riekert

The demand for efficient processing of deep neural networks (DNNs) on embedded devices is a significant challenge limiting their deployment. Exploiting sparsity in the network's feature maps is one of the ways to reduce its inference…

Computer Vision and Pattern Recognition · Computer Science 2023-09-28 Matteo Grimaldi , Darshan C. Ganji , Ivan Lazarevich , Sudhakar Sah

This study introduces a novel activation function, characterized by a dynamic slope that adjusts throughout the training process, aimed at enhancing adaptability and performance in deep neural networks for computer vision tasks. The…

Computer Vision and Pattern Recognition · Computer Science 2024-08-20 Archisman Chakraborti , Bidyut B Chaudhuri

We identify and study two common failure modes for early training in deep ReLU nets. For each we give a rigorous proof of when it occurs and how to avoid it, for fully connected and residual architectures. The first failure mode,…

Machine Learning · Statistics 2018-11-14 Boris Hanin , David Rolnick

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

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

In this article we investigate blow up phenomena for gradient descent optimization methods in the training of artificial neural networks (ANNs). Our theoretical analysis is focused on shallow ANNs with one neuron on the input layer, one…

Optimization and Control · Mathematics 2022-11-29 Davide Gallon , Arnulf Jentzen , Felix Lindner

Activation functions are fundamental elements of deep learning architectures as they significantly influence training dynamics. ReLU, while widely used, is prone to the dying neuron problem, which has been mitigated by variants such as…

Machine Learning · Computer Science 2025-05-22 Indrashis Das , Mahmoud Safari , Steven Adriaensen , Frank Hutter
‹ Prev 1 4 5 6 7 8 10 Next ›