English
Related papers

Related papers: How Do Adam and Training Strategies Help BNNs Opti…

200 papers

Continual learning entails learning a sequence of tasks and balancing their knowledge appropriately. With limited access to old training samples, much of the current work in deep neural networks has focused on overcoming catastrophic…

Machine Learning · Computer Science 2023-10-16 Yilin Lyu , Liyuan Wang , Xingxing Zhang , Zicheng Sun , Hang Su , Jun Zhu , Liping Jing

Neural network binarization accelerates deep models by quantizing their weights and activations into 1-bit. However, there is still a huge performance gap between Binary Neural Networks (BNNs) and their full-precision (FP) counterparts. As…

Computer Vision and Pattern Recognition · Computer Science 2022-07-19 Yuzhang Shang , Dan Xu , Ziliang Zong , Liqiang Nie , Yan Yan

Binary Neural Networks (BNNs) show great promise for real-world embedded devices. As one of the critical steps to achieve a powerful BNN, the scale factor calculation plays an essential role in reducing the performance gap to their…

Computer Vision and Pattern Recognition · Computer Science 2022-09-07 Sheng Xu , Yanjing Li , Tiancheng Wang , Teli Ma , Baochang Zhang , Peng Gao , Yu Qiao , Jinhu Lv , Guodong Guo

The lack of mathematical tractability of Deep Neural Networks (DNNs) has hindered progress towards having a unified convergence analysis of training algorithms, in the general setting. We propose a unified optimization framework for…

Machine Learning · Computer Science 2018-05-24 Hadi Ghauch , Hossein Shokri-Ghadikolaei , Carlo Fischione , Mikael Skoglund

First-order optimization methods are currently the mainstream in training deep neural networks (DNNs). Optimizers like Adam incorporate limited curvature information by employing the diagonal matrix preconditioning of the stochastic…

Machine Learning · Computer Science 2025-03-12 Damien Martins Gomes , Yanlei Zhang , Eugene Belilovsky , Guy Wolf , Mahdi S. Hosseini

During training, the weights of a Deep Neural Network (DNN) are optimized from a random initialization towards a nearly optimum value minimizing a loss function. Only this final state of the weights is typically kept for testing, while the…

Machine Learning · Computer Science 2021-03-26 Gianni Franchi , Andrei Bursuc , Emanuel Aldea , Severine Dubuisson , Isabelle Bloch

Adam is the default algorithm for training neural networks, including large language models (LLMs). However, \citet{reddi2019convergence} provided an example that Adam diverges, raising concerns for its deployment in AI model training. We…

Machine Learning · Computer Science 2026-03-03 Yushun Zhang , Bingran Li , Congliang Chen , Zhi-Quan Luo , Ruoyu Sun

Binary neural network (BNN) is an extreme quantization version of convolutional neural networks (CNNs) with all features and weights mapped to just 1-bit. Although BNN saves a lot of memory and computation demand to make CNN applicable on…

Computer Vision and Pattern Recognition · Computer Science 2022-07-20 Xulong Shi , Zhi Qi , Jiaxuan Cai , Keqi Fu , Yaru Zhao , Zan Li , Xuanyu Liu , Hao Liu

The performance of a neural network for a given task is largely determined by the initial calibration of the network parameters. Yet, it has been shown that the calibration, also referred to as training, is generally NP-complete. This…

Quantum Physics · Physics 2019-11-21 Yidong Liao , Daniel Ebler , Feiyang Liu , Oscar Dahlsten

This paper introduces EXAdam ($\textbf{EX}$tended $\textbf{Adam}$), a novel optimization algorithm that builds upon the widely-used Adam optimizer. EXAdam incorporates two key enhancements: (1) new debiasing terms for improved moment…

Machine Learning · Computer Science 2025-05-19 Ahmed M. Adly

Stochastic gradient descent-based algorithms are widely used for training deep neural networks but often suffer from slow convergence. To address the challenge, we leverage the framework of the alternating direction method of multipliers…

Machine Learning · Computer Science 2025-02-03 Ouya Wang , Shenglong Zhou , Geoffrey Ye Li

Transformers are difficult to optimize with stochastic gradient descent (SGD) and largely rely on adaptive optimizers such as Adam. Despite their empirical success, the reasons behind Adam's superior performance over SGD remain poorly…

Machine Learning · Computer Science 2026-02-19 Akiyoshi Tomihari , Issei Sato

In recent studies, several asymptotic upper bounds on generalization errors on deep neural networks (DNNs) are theoretically derived. These bounds are functions of several norms of weights of the DNNs, such as the Frobenius and spectral…

Machine Learning · Computer Science 2019-05-23 Mete Ozay

Previous studies dominantly target at self-supervised learning on real-valued networks and have achieved many promising results. However, on the more challenging binary neural networks (BNNs), this task has not yet been fully explored in…

Computer Vision and Pattern Recognition · Computer Science 2021-06-22 Zhiqiang Shen , Zechun Liu , Jie Qin , Lei Huang , Kwang-Ting Cheng , Marios Savvides

Is the standard weight decay in AdamW truly optimal? Although AdamW decouples weight decay from adaptive gradient scaling, a fundamental conflict remains: the Radial Tug-of-War. In deep learning, gradients tend to increase parameter norms…

Machine Learning · Computer Science 2026-02-06 Hao Chen , Jinghui Yuan , Hanmin Zhang

Optimization algorithms are core methods by which machine learning models iteratively minimize loss functions, update parameters, learn from data, and improve performance. Momentum SGD and AdamW represent two important optimization…

Machine Learning · Computer Science 2026-05-21 Meng Zhu , Quan Xiao , Weidong Min

A biologically plausible method for training an Artificial Neural Network (ANN) involves treating each unit as a stochastic Reinforcement Learning (RL) agent, thereby considering the network as a team of agents. Consequently, all units can…

Machine Learning · Computer Science 2023-07-26 Stephen Chung

Batch normalization (BN) is a key facilitator and considered essential for state-of-the-art binary neural networks (BNN). However, the BN layer is costly to calculate and is typically implemented with non-binary parameters, leaving a hurdle…

Machine Learning · Computer Science 2021-04-19 Tianlong Chen , Zhenyu Zhang , Xu Ouyang , Zechun Liu , Zhiqiang Shen , Zhangyang Wang

We propose a continuous-time scheme for large-scale optimization that introduces individual, adaptive momentum coefficients regulated by the kinetic energy of each model parameter. This approach automatically adjusts to local landscape…

Machine Learning · Computer Science 2026-02-03 Aikaterini Karoni , Rajit Rajpal , Benedict Leimkuhler , Gabriel Stoltz

In contrast to SGD, adaptive gradient methods like Adam allow robust training of modern deep networks, especially large language models. However, the use of adaptivity not only comes at the cost of extra memory but also raises the…

Machine Learning · Computer Science 2022-07-20 Zhiyuan Li , Srinadh Bhojanapalli , Manzil Zaheer , Sashank J. Reddi , Sanjiv Kumar