English
Related papers

Related papers: Deconstructing What Makes a Good Optimizer for Lan…

200 papers

We formulate the problem of neural network optimization as Bayesian filtering, where the observations are the backpropagated gradients. While neural network optimization has previously been studied using natural gradient methods which are…

Machine Learning · Statistics 2020-04-17 Laurence Aitchison

Gradient-based first-order adaptive optimization methods such as the Adam optimizer are prevalent in training artificial networks, achieving the state-of-the-art results. This work attempts to answer the question whether it is viable for…

Neural and Evolutionary Computing · Computer Science 2022-12-20 Yukun Yang , Peng Li

Adaptive optimization algorithms such as Adam are widely used in deep learning. The stability of such algorithms is often improved with a warmup schedule for the learning rate. Motivated by the difficulty of choosing and tuning warmup…

Machine Learning · Computer Science 2021-03-23 Jerry Ma , Denis Yarats

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

Optimization algorithms are widely employed to tackle complex problems, but designing them manually is often labor-intensive and requires significant expertise. Global placement is a fundamental step in electronic design automation (EDA).…

Neural and Evolutionary Computing · Computer Science 2025-04-28 Xufeng Yao , Jiaxi Jiang , Yuxuan Zhao , Peiyu Liao , Yibo Lin , Bei Yu

When training neural models, it is common to combine multiple loss terms. The balancing of these terms requires considerable human effort and is computationally demanding. Moreover, the optimal trade-off between the loss term can change as…

Machine Learning · Computer Science 2020-06-29 Itzik Malkiel , Lior Wolf

Adaptive gradient methods, especially Adam-type methods (such as Adam, AMSGrad, and AdaBound), have been proposed to speed up the training process with an element-wise scaling term on learning rates. However, they often generalize poorly…

Machine Learning · Computer Science 2021-07-20 Zhou Shao , Tong Lin

In this paper, we introduce StochGradAdam, a novel optimizer designed as an extension of the Adam algorithm, incorporating stochastic gradient sampling techniques to improve computational efficiency while maintaining robust performance.…

Machine Learning · Computer Science 2025-03-19 Juyoung Yun

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

The insufficient generalization of adaptive moment estimation (Adam) has hindered its broader application. Recent studies have shown that flat minima in loss landscapes are highly associated with improved generalization. Inspired by the…

Machine Learning · Computer Science 2024-12-18 Long Jin , Han Nong , Liangming Chen , Zhenming Su

This paper establishes a mathematical foundation for the Adam optimizer, elucidating its connection to natural gradient descent through Riemannian and information geometry. We provide an accessible and detailed analysis of the diagonal…

Machine Learning · Computer Science 2024-09-05 Dongseong Hwang

In this paper, we propose a continuous-time formulation for the AdaGrad, RMSProp, and Adam optimization algorithms by modeling them as first-order integro-differential equations. We perform numerical simulations of these equations, along…

Machine Learning · Computer Science 2025-10-14 Carlos Heredia

The Conformer has become the most popular encoder model for automatic speech recognition (ASR). It adds convolution modules to a transformer to learn both local and global dependencies. In this work we describe a faster, more…

Audio and Speech Processing · Electrical Eng. & Systems 2024-04-11 Zengwei Yao , Liyong Guo , Xiaoyu Yang , Wei Kang , Fangjun Kuang , Yifan Yang , Zengrui Jin , Long Lin , Daniel Povey

As deep learning models exponentially increase in size, optimizers such as Adam encounter significant memory consumption challenges due to the storage of first and second moment data. Current memory-efficient methods like Adafactor and CAME…

Machine Learning · Computer Science 2024-03-25 Pengxiang Zhao , Ping Li , Yingjie Gu , Yi Zheng , Stephan Ludger Kölker , Zhefeng Wang , Xiaoming Yuan

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

Gradient descent based optimization methods are the methods of choice to train deep neural networks in machine learning. Beyond the standard gradient descent method, also suitable modified variants of standard gradient descent involving…

Optimization and Control · Mathematics 2025-04-29 Steffen Dereich , Arnulf Jentzen , Adrian Riekert

AdamZ is an advanced variant of the Adam optimiser, developed to enhance convergence efficiency in neural network training. This optimiser dynamically adjusts the learning rate by incorporating mechanisms to address overshooting and…

Machine Learning · Computer Science 2024-11-26 Ilia Zaznov , Atta Badii , Alfonso Dufour , Julian Kunkel

Deep learning optimizers are often motivated through a mix of convex and approximate second-order theory. We select three such methods -- Adam, Shampoo and Prodigy -- and argue that each method can instead be understood as a squarely…

Machine Learning · Computer Science 2024-12-09 Jeremy Bernstein , Laker Newhouse

Large-scale machine learning training, in particular distributed stochastic gradient descent, needs to be robust to inherent system variability such as node straggling and random communication delays. This work considers a distributed…

Machine Learning · Computer Science 2019-03-08 Jianyu Wang , Gauri Joshi

Adaptive gradient algorithm (AdaGrad) and its variants, such as RMSProp, Adam, AMSGrad, etc, have been widely used in deep learning. Although these algorithms are faster in the early phase of training, their generalization performance is…

Machine Learning · Computer Science 2021-09-14 Kun Zeng , Jinlan Liu , Zhixia Jiang , Dongpo Xu