English
Related papers

Related papers: How to Fine-Tune Vision Models with SGD

200 papers

Adaptive gradient methods such as Adam have gained increasing popularity in deep learning optimization. However, it has been observed that compared with (stochastic) gradient descent, Adam can converge to a different solution with a…

Machine Learning · Computer Science 2021-08-26 Difan Zou , Yuan Cao , Yuanzhi Li , Quanquan Gu

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

Recent advancements in deep learning optimization have introduced new algorithms, such as Schedule-Free optimizers, AdEMAMix, MARS and Lion which modify traditional momentum mechanisms. In a separate line of work, theoretical acceleration…

Machine Learning · Computer Science 2025-02-05 Depen Morwani , Nikhil Vyas , Hanlin Zhang , Sham Kakade

The challenge of overfitting, in which the model memorizes the training data and fails to generalize to test data, has become increasingly significant in the training of large neural networks. To tackle this challenge, Sharpness-Aware…

Machine Learning · Computer Science 2023-10-12 Zixiang Chen , Junkai Zhang , Yiwen Kou , Xiangning Chen , Cho-Jui Hsieh , Quanquan Gu

When training Convolutional Neural Networks (CNNs) there is a large emphasis on creating efficient optimization algorithms and highly accurate networks. The state-of-the-art method of optimizing the networks is done by using gradient…

Neural and Evolutionary Computing · Computer Science 2023-01-24 Manuel Bradicic , Michal Sitarz , Felix Sylvest Olesen

This paper formalizes and analyzes Gaussian smoothing applied to two prominent optimization methods: Stochastic Gradient Descent (GSmoothSGD) and Adam (GSmoothAdam) in deep learning. By attenuating small fluctuations, Gaussian smoothing…

Optimization and Control · Mathematics 2024-11-19 Andrew Starnes , Clayton Webster

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

We design and implement a distributed multinode synchronous SGD algorithm, without altering hyper parameters, or compressing data, or altering algorithmic behavior. We perform a detailed analysis of scaling, and identify optimal design…

Distributed, Parallel, and Cluster Computing · Computer Science 2016-03-02 Dipankar Das , Sasikanth Avancha , Dheevatsa Mudigere , Karthikeyan Vaidynathan , Srinivas Sridharan , Dhiraj Kalamkar , Bharat Kaul , Pradeep Dubey

We revisit the choice of SGD for training deep neural networks by reconsidering the appropriate geometry in which to optimize the weights. We argue for a geometry invariant to rescaling of weights that does not affect the output of the…

Machine Learning · Computer Science 2015-06-09 Behnam Neyshabur , Ruslan Salakhutdinov , Nathan Srebro

Recently, Muon and related spectral optimizers have demonstrated strong empirical performance as scalable stochastic methods, often outperforming Adam. Yet their behaviour remains poorly understood. We analyze stochastic spectral…

Optimization and Control · Mathematics 2026-05-12 Elliot Paquette , Noah Marshall , Lucas Benigni , Guangyuan Wang , Atish Agarwala , Courtney Paquette

Nesterov SGD is widely used for training modern neural networks and other machine learning models. Yet, its advantages over SGD have not been theoretically clarified. Indeed, as we show in our paper, both theoretically and empirically,…

Machine Learning · Computer Science 2019-09-30 Chaoyue Liu , Mikhail Belkin

We consider distributed optimization under communication constraints for training deep learning models. We propose a new algorithm, whose parameter updates rely on two forces: a regular gradient step, and a corrective direction dictated by…

Machine Learning · Computer Science 2022-04-29 Yunfei Teng , Wenbo Gao , Francois Chalus , Anna Choromanska , Donald Goldfarb , Adrian Weller

This study proposes NIRMAL (Novel Integrated Robust Multi-Adaptation Learning), a novel optimization algorithm that combines multiple strategies inspired by the movements of the chess piece. These strategies include gradient descent,…

Information Retrieval · Computer Science 2025-08-07 Nirmal Gaud , Surej Mouli , Preeti Katiyar , Vaduguru Venkata Ramya

We propose NovoGrad, an adaptive stochastic gradient descent method with layer-wise gradient normalization and decoupled weight decay. In our experiments on neural networks for image classification, speech recognition, machine translation,…

Stochastic Gradient Descent (SGD) is an out-of-equilibrium algorithm used extensively to train artificial neural networks. However very little is known on to what extent SGD is crucial for to the success of this technology and, in…

Machine Learning · Computer Science 2023-12-19 Persia Jana Kamali , Pierfrancesco Urbani

Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse natural language processing benchmarks. However, the escalating scale of model parameters imposes prohibitive memory overheads during training,…

Machine Learning · Computer Science 2026-04-28 Ziqing Wen , Ping Luo , Jiahuan Wang , Kun Yuan , Dongsheng Li , Tao Sun

A framework is introduced for solving a sequence of slowly changing optimization problems, including those arising in regression and classification applications, using optimization algorithms such as stochastic gradient descent (SGD). The…

Machine Learning · Computer Science 2015-09-25 Craig Wilson , Venugopal V. Veeravalli

Asynchronous stochastic gradient descent (SGD) is attractive from a speed perspective because workers do not wait for synchronization. However, the Transformer model converges poorly with asynchronous SGD, resulting in substantially lower…

Computation and Language · Computer Science 2021-11-30 Alham Fikri Aji , Kenneth Heafield

It is known that the standard stochastic gradient descent (SGD) optimization method, as well as accelerated and adaptive SGD optimization methods such as the Adam optimizer fail to converge if the learning rates do not converge to zero (as,…

Optimization and Control · Mathematics 2024-06-21 Steffen Dereich , Arnulf Jentzen , Adrian Riekert

Gradient based optimization methods are the established state-of-the-art paradigm to study strongly entangled quantum systems in two dimensions with Projected Entangled Pair States. However, the key ingredient, the gradient itself, has…

Quantum Physics · Physics 2025-04-15 Anna Francuz , Norbert Schuch , Bram Vanhecke