English
Related papers

Related papers: The AdEMAMix Optimizer: Better, Faster, Older

200 papers

Learning rate adaptation is a popular topic in machine learning. Gradient Descent trains neural nerwork with a fixed learning rate. Learning rate adaptation is proposed to accelerate the training process through adjusting the step size in…

Machine Learning · Computer Science 2022-10-20 Bozhou Chen , Hongzhi Wang , Chenmin Ba

Momentum is a popular technique for improving convergence rates during gradient descent. In this research, we experiment with adding momentum to the Baum-Welch expectation-maximization algorithm for training Hidden Markov Models. We compare…

Machine Learning · Computer Science 2022-06-10 Andrew Miller , Fabio Di Troia , Mark Stamp

Adaptive gradient methods for stochastic optimization adjust the learning rate for each parameter locally. However, there is also a global learning rate which must be tuned in order to get the best performance. In this paper, we present a…

Machine Learning · Computer Science 2018-06-12 Hiroaki Hayashi , Jayanth Koushik , Graham Neubig

We present a genetic algorithm framework for automatically discovering deep learning optimization algorithms. Our approach encodes optimizers as genomes that specify combinations of primitive update terms (gradient, momentum, RMS…

Neural and Evolutionary Computing · Computer Science 2025-12-16 Mitchell Marfinetz

We introduce Gravity, another algorithm for gradient-based optimization. In this paper, we explain how our novel idea change parameters to reduce the deep learning model's loss. It has three intuitive hyper-parameters that the best values…

Machine Learning · Computer Science 2021-01-25 Dariush Bahrami , Sadegh Pouriyan Zadeh

In this work and its accompanying Part II [1], we develop an accelerated algorithmic framework, DAMA (Decentralized Accelerated Minimax Approach), for nonconvex Polyak-Lojasiewicz minimax optimization over decentralized multi-agent…

Optimization and Control · Mathematics 2025-12-17 Haoyuan Cai , Sulaiman A. Alghunaim , Ali H. Sayed

Adaptive gradient methods such as RMSProp and Adam use exponential moving estimate of the squared gradient to compute adaptive step sizes, achieving better convergence than SGD in face of noisy objectives. However, Adam can have undesirable…

Machine Learning · Computer Science 2021-07-06 Chen Zhu , Yu Cheng , Zhe Gan , Furong Huang , Jingjing Liu , Tom Goldstein

Training large language models (LLMs) typically involves pre-training on massive corpora, only to restart the process entirely when new data becomes available. A more efficient and resource-conserving approach would be continual…

As a well-known optimization framework, the Alternating Direction Method of Multipliers (ADMM) has achieved tremendous success in many classification and regression applications. Recently, it has attracted the attention of deep learning…

Machine Learning · Computer Science 2021-12-23 Junxiang Wang , Hongyi Li , Liang Zhao

Delays and asynchrony are inevitable in large-scale machine-learning problems where communication plays a key role. As such, several works have extensively analyzed stochastic optimization with delayed gradients. However, as far as we are…

Machine Learning · Computer Science 2023-08-28 Arman Adibi , Aritra Mitra , Hamed Hassani

Stochastic gradient-based descent (SGD), have long been central to training large language models (LLMs). However, their effectiveness is increasingly being questioned, particularly in large-scale applications where empirical evidence…

Machine Learning · Computer Science 2025-07-03 Di Zhang , Yihang Zhang

Large language models (LLMs) have demonstrated remarkable performance due to their large parameter counts and extensive training data. However, their scale leads to significant memory bottlenecks during training, especially when using…

Machine Learning · Computer Science 2026-05-14 Ziqing Wen , Jiahuan Wang , Ping Luo , Dongsheng Li , Tao Sun

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 convergence and generalization when training the deep neural network…

Machine Learning · Computer Science 2024-04-09 Lei Guan , Dongsheng Li , Yanqi Shi , Jian Meng

In this paper, we provide a rigorous proof of convergence of the Adaptive Moment Estimate (Adam) algorithm for a wide class of optimization objectives. Despite the popularity and efficiency of the Adam algorithm in training deep neural…

Optimization and Control · Mathematics 2023-11-08 Haochuan Li , Alexander Rakhlin , Ali Jadbabaie

Quantizing optimizer states is becoming an important ingredient of memory-efficient large-scale pre-training, but the resulting optimizer dynamics remain only partially understood. We study low-precision exponential moving average (EMA)…

Machine Learning · Computer Science 2026-03-18 Kristi Topollai , Anna Choromanska

First-order stochastic optimization methods are currently the most widely used class of methods for training deep neural networks. However, the choice of the optimizer has become an ad-hoc rule that can significantly affect the performance.…

Machine Learning · Computer Science 2020-10-21 Samy Jelassi , Aaron Defazio

We propose EMMA, an efficient and unified architecture for multimodal understanding, generation and editing. Specifically, EMMA primarily consists of 1) An efficient autoencoder with a 32x compression ratio, which significantly reduces the…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Xin He , Longhui Wei , Jianbo Ouyang , Minghui Liao , Lingxi Xie , Qi Tian

Optimization is essential in deep learning. The foundational method upon which most optimizers are built is momentum-based stochastic gradient descent. However, it suffers from two key drawbacks. First, it has noisy and varying gradients,…

Machine Learning · Computer Science 2026-05-22 Saurabh Saini , Kapil Ahuja , Thomas Wick , Saurav Kumar

This paper presents a novel neural network training approach for faster convergence and better generalization abilities in deep reinforcement learning. Particularly, we focus on the enhancement of training and evaluation performance in…

Machine Learning · Computer Science 2020-05-26 Mohammed Sharafath Abdul Hameed , Gavneet Singh Chadha , Andreas Schwung , Steven X. Ding

Adaptive optimizers, such as Adam, have achieved remarkable success in deep learning. A key component of these optimizers is the so-called preconditioning matrix, providing enhanced gradient information and regulating the step size of each…

Machine Learning · Computer Science 2024-12-10 Yun Yue , Zhiling Ye , Jiadi Jiang , Yongchao Liu , Ke Zhang