English
Related papers

Related papers: Momentum Centering and Asynchronous Update for Ada…

200 papers

Adaptive gradient methods have become recently very popular, in particular as they have been shown to be useful in the training of deep neural networks. In this paper we have analyzed RMSProp, originally proposed for the training of deep…

Machine Learning · Computer Science 2017-11-29 Mahesh Chandra Mukkamala , Matthias Hein

We introduce MVN-Grad (Momentum on Variance-Normalized Gradients), an Adam-style optimizer that improves stability and performance by combining two complementary ideas: variance-based normalization and momentum applied after normalization.…

Machine Learning · Computer Science 2026-02-12 Francisco Patitucci , Aryan Mokhtari

Gradient descent is an important class of iterative algorithms for minimizing convex functions. Classically, gradient descent has been a sequential and synchronous process. Distributed and asynchronous variants of gradient descent have been…

Optimization and Control · Mathematics 2014-12-02 Yun Kuen Cheung , Richard Cole

Reinforcement learning from human feedback (RLHF) shows promise for aligning diffusion and flow models, yet policy optimization methods such as GRPO suffer from inefficient and static sampling strategies. These methods treat all prompts and…

Machine Learning · Computer Science 2026-02-09 Yuming Li , Qingyu Li , Chengyu Bai , Xiangyang Luo , Zeyue Xue , Wenyu Qin , Meng Wang , Yikai Wang , Shanghang Zhang

Although adaptive gradient methods have been extensively used in deep learning, their convergence rates proved in the literature are all slower than that of SGD, particularly with respect to their dependence on the dimension. This paper…

Optimization and Control · Mathematics 2025-04-29 Huan Li , Yiming Dong , Zhouchen Lin

Parameter-efficient fine-tuning strategies for foundation models in 1D textual and 2D visual analysis have demonstrated remarkable efficacy. However, due to the scarcity of point cloud data, pre-training large 3D models remains a…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Mengke Li , Lihao Chen , Peng Zhang , Yiu-ming Cheung , Hui Huang

Stochastic Gradient Decent (SGD) is one of the core techniques behind the success of deep neural networks. The gradient provides information on the direction in which a function has the steepest rate of change. The main problem with basic…

The alternating direction method of multipliers (ADMM) is commonly used for distributed model fitting problems, but its performance and reliability depend strongly on user-defined penalty parameters. We study distributed ADMM methods that…

Machine Learning · Computer Science 2017-06-21 Zheng Xu , Gavin Taylor , Hao Li , Mario Figueiredo , Xiaoming Yuan , Tom Goldstein

Since the 21st century, artificial intelligence has been leading a new round of industrial revolution. Under the training framework, the optimization algorithm aims to stably converge high-dimensional optimization to local and even global…

Machine Learning · Computer Science 2025-12-02 Meng Zhu , Quan Xiao , Weidong Min

The dynamic behavior of RMSprop and Adam algorithms is studied through a combination of careful numerical experiments and theoretical explanations. Three types of qualitative features are observed in the training loss curve: fast initial…

Machine Learning · Computer Science 2021-10-01 Chao Ma , Lei Wu , Weinan E

We develop an Accelerated Back Pressure (ABP) algorithm using Accelerated Dual Descent (ADD), a distributed approximate Newton-like algorithm that only uses local information. Our construction is based on writing the backpressure algorithm…

Optimization and Control · Mathematics 2013-02-07 Michael Zargham , Alejandro Ribeiro , Ali Jadbabaie

The optimization algorithm and its hyperparameters can significantly affect the training speed and resulting model accuracy in machine learning applications. The wish list for an ideal optimizer includes fast and smooth convergence to low…

Machine Learning · Computer Science 2024-02-20 Marco Eckhoff , Markus Reiher

The convolutional neural networks (CNNs) are generally trained using stochastic gradient descent (SGD) based optimization techniques. The existing SGD optimizers generally suffer with the overshooting of the minimum and oscillation near…

Machine Learning · Computer Science 2022-09-20 Shiv Ram Dubey , S. H. Shabbeer Basha , Satish Kumar Singh , Bidyut Baran Chaudhuri

Modern GPUs are equipped with large amounts of high-bandwidth memory, enabling them to support mini-batch sizes of up to tens of thousands of training samples. However, most existing optimizers struggle to perform effectively at such a…

Machine Learning · Computer Science 2026-02-10 Yishun Lu , Wesley Armour

Pre-trained Vision-Language Models (VLMs) have recently shown promise in detecting anomalies. However, previous approaches are fundamentally limited by their reliance on human-designed prompts and the lack of accessible anomaly samples,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-25 Pi-Wei Chen , Jerry Chun-Wei Lin , Wei-Han Chen , Jia Ji , Zih-Ching Chen , Feng-Hao Yeh , Chao-Chun Chen

This paper considers the problem of asynchronous stochastic nonconvex optimization with heavy-tailed gradient noise and arbitrarily heterogeneous computation times across workers. We propose an asynchronous normalized stochastic gradient…

Optimization and Control · Mathematics 2026-01-28 Yidong Wu , Luo Luo

We propose AdaMuon, a novel optimizer that combines element-wise adaptivity with orthogonal updates for large-scale neural network training. AdaMuon incorporates two tightly coupled mechanisms: (1) an element-wise second momentum estimator…

Machine Learning · Computer Science 2025-12-25 Chongjie Si , Debing Zhang , Wei Shen

Parameter-Efficient Fine-Tuning (PEFT) method has emerged as a dominant paradigm for adapting pre-trained GNN models to downstream tasks. However, existing PEFT methods usually exhibit significant vulnerability to various noise and attacks…

Machine Learning · Computer Science 2026-01-05 Ziyan Zhang , Bo Jiang , Jin Tang

Adaptive moment methods have been remarkably successful in deep learning optimization, particularly in the presence of noisy and/or sparse gradients. We further the advantages of adaptive moment techniques by proposing a family of double…

Machine Learning · Statistics 2018-11-07 Kin Gutierrez , Jin Li , Cristian Challu , Artur Dubrawski

Hyperparameter tuning is one of the most time-consuming workloads in deep learning. State-of-the-art optimizers, such as AdaGrad, RMSProp and Adam, reduce this labor by adaptively tuning an individual learning rate for each variable.…

Machine Learning · Statistics 2018-02-16 Jian Zhang , Ioannis Mitliagkas