English
Related papers

Related papers: AdAdaGrad: Adaptive Batch Size Schemes for Adaptiv…

200 papers

Distributed implementations of mini-batch stochastic gradient descent (SGD) suffer from communication overheads, attributed to the high frequency of gradient updates inherent in small-batch training. Training with large batches can reduce…

Machine Learning · Statistics 2018-06-12 Lingjiao Chen , Hongyi Wang , Jinman Zhao , Dimitris Papailiopoulos , Paraschos Koutris

Scheduling the batch size to increase is an effective strategy to control gradient noise when training deep neural networks. Current approaches implement scheduling heuristics that neglect structure within the optimization procedure,…

Machine Learning · Computer Science 2022-05-18 Calum Robert MacLellan , Feng Dong

Adaptive gradient methods have been increasingly adopted by deep learning community due to their fast convergence and reduced sensitivity to hyper-parameters. However, these methods come with limitations, such as increased memory…

Machine Learning · Computer Science 2024-12-17 Corrado Coppola , Lorenzo Papa , Irene Amerini , Laura Palagi

The classical AdaGrad method adapts the learning rate by dividing by the square root of a sum of squared gradients. Because this sum on the denominator is increasing, the method can only decrease step sizes over time, and requires a…

Machine Learning · Computer Science 2022-06-15 Aaron Defazio , Baoyu Zhou , Lin Xiao

We introduce LDAdam, a memory-efficient optimizer for training large models, that performs adaptive optimization steps within lower dimensional subspaces, while consistently exploring the full parameter space during training. This strategy…

Machine Learning · Computer Science 2025-03-04 Thomas Robert , Mher Safaryan , Ionut-Vlad Modoranu , Dan Alistarh

We explore an explicit link between stochastic gradient descent using common batching strategies and splitting methods for ordinary differential equations. From this perspective, we introduce a new minibatching strategy (called Symmetric…

Optimization and Control · Mathematics 2025-04-08 Luke Shaw , Peter A. Whalley

In the recent years, various gradient descent algorithms including the methods of gradient descent, gradient descent with momentum, adaptive gradient (AdaGrad), root-mean-square propagation (RMSProp) and adaptive moment estimation (Adam)…

Machine Learning · Computer Science 2024-09-19 Abel C. H. Chen

In this paper we propose several adaptive gradient methods for stochastic optimization. Unlike AdaGrad-type of methods, our algorithms are based on Armijo-type line search and they simultaneously adapt to the unknown Lipschitz constant of…

Large-batch training has become a commonly used technique when training neural networks with a large number of GPU/TPU processors. As batch size increases, stochastic optimizers tend to converge to sharp local minima, leading to degraded…

Machine Learning · Computer Science 2022-01-25 Yong Liu , Xiangning Chen , Minhao Cheng , Cho-Jui Hsieh , Yang You

Despite their popularity, deep neural networks (DNNs) applied to time series forecasting often fail to beat simpler statistical models. One of the main causes of this suboptimal performance is the data non-stationarity present in many…

Machine Learning · Computer Science 2024-10-08 Edoardo Urettini , Daniele Atzeni , Reshawn J. Ramjattan , Antonio Carta

Stochastic gradient methods are among the most widely used algorithms for large-scale optimization and machine learning. A key technique for improving the statistical efficiency and stability of these methods is the use of averaging schemes…

Optimization and Control · Mathematics 2026-03-11 K. Lakshmanan

A major obstacle to achieving global convergence in distributed and federated learning is the misalignment of gradients across clients, or mini-batches due to heterogeneity and stochasticity of the distributed data. In this work, we show…

Machine Learning · Computer Science 2021-12-14 Yatin Dandi , Luis Barba , Martin Jaggi

We analyze the learning properties of the stochastic gradient method when multiple passes over the data and mini-batches are allowed. We study how regularization properties are controlled by the step-size, the number of passes and the…

Machine Learning · Computer Science 2019-03-18 Junhong Lin , Lorenzo Rosasco

Adaptive gradient-based optimization methods such as \textsc{Adagrad}, \textsc{Rmsprop}, and \textsc{Adam} are widely used in solving large-scale machine learning problems including deep learning. A number of schemes have been proposed in…

Machine Learning · Computer Science 2019-05-30 Parvin Nazari , Davoud Ataee Tarzanagh , George Michailidis

In this paper, we introduce AdaSelection, an adaptive sub-sampling method to identify the most informative sub-samples within each minibatch to speed up the training of large-scale deep learning models without sacrificing model performance.…

Machine Learning · Computer Science 2023-06-21 Minghe Zhang , Chaosheng Dong , Jinmiao Fu , Tianchen Zhou , Jia Liang , Jia Liu , Bo Liu , Michinari Momma , Bryan Wang , Yan Gao , Yi Sun

Selecting an effective step-size is a fundamental challenge in first-order optimization, especially for problems with non-Euclidean geometries. This paper presents a novel adaptive step-size strategy for optimization algorithms that rely on…

Optimization and Control · Mathematics 2025-10-14 Abbas Khademi , Antonio Silveti-Falls

The success of deep learning can be attributed to various factors such as increase in computational power, large datasets, deep convolutional neural networks, optimizers etc. Particularly, the choice of optimizer affects the generalization,…

Machine Learning · Computer Science 2021-09-10 Anirudh Maiya , Inumella Sricharan , Anshuman Pandey , Srinivas K. S

Recent advances in image synthesis have been propelled by powerful generative models, such as Masked Generative Transformers (MaskGIT), autoregressive models, diffusion models, and rectified flow models. A common principle behind their…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Zanlin Ni , Yulin Wang , Yeguo Hua , Renping Zhou , Jiayi Guo , Jun Song , Bo Zheng , Gao Huang

In this study, we revisit the convergence of AdaGrad with momentum (covering AdaGrad as a special case) on non-convex smooth optimization problems. We consider a general noise model where the noise magnitude is controlled by the function…

Optimization and Control · Mathematics 2024-09-16 Yusu Hong , Junhong Lin

We propose a computationally-friendly adaptive learning rate schedule, "AdaLoss", which directly uses the information of the loss function to adjust the stepsize in gradient descent methods. We prove that this schedule enjoys linear…

Machine Learning · Statistics 2021-09-20 Xiaoxia Wu , Yuege Xie , Simon Du , Rachel Ward
‹ Prev 1 8 9 10 Next ›