L Guan, D Li, Y Shi, J Meng - IEEE Transactions on Pattern …, 2024 - ieeexplore.ieee.org
In this paper, we propose a general deep learning training framework XGrad which introduces weight prediction into the popular gradient-based optimizers to boost their …
D Shulman - arXiv preprint arXiv:2302.09566, 2023 - arxiv.org
In recent years, deep learning has achieved remarkable success in various fields such as image recognition, natural language processing, and speech recognition. The effectiveness …
Z Zhang, L Ma, Z Li, C Wu - arXiv preprint arXiv:1709.04546, 2017 - arxiv.org
Adaptive optimization algorithms, such as Adam and RMSprop, have shown better optimization performance than stochastic gradient descent (SGD) in some scenarios …
SR Dubey, SK Singh… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
The stochastic gradient descent (SGD) optimizers are generally used to train the convolutional neural networks (CNNs). In recent years, several adaptive momentum based …
L Xia, S Massei - arXiv preprint arXiv:2312.15295, 2023 - arxiv.org
Adaptive first-order optimizers are fundamental tools in deep learning, although they may suffer from poor generalization due to the nonuniform gradient scaling. In this work, we …
C Desai - International Journal of Innovative Science and …, 2020 - researchgate.net
The role of optimizer in deep neural networks model impacts the accuracy of the model. Deep learning comes under the umbrella of parametric approaches; however, it tries to relax …
S Wang, J Sun, Z Xu - Proceedings of the AAAI Conference on Artificial …, 2019 - aaai.org
Deep neural networks are traditionally trained using humandesigned stochastic optimization algorithms, such as SGD and Adam. Recently, the approach of learning to optimize network …
Abstract Stochastic Gradient Decent (SGD) is a very popular basic optimizer applied in the learning algorithms of deep neural networks. However, it has fixed-sized steps for every …
Y Yu, F Liu - IEEE Access, 2019 - ieeexplore.ieee.org
First-order gradient-based optimization algorithms have been of core practical importance in the field of deep learning. In this paper, we propose a new weighting mechanism-based first …