English
Related papers

Related papers: Inefficiency of K-FAC for Large Batch Size Trainin…

200 papers

Asynchronous distributed algorithms are a popular way to reduce synchronization costs in large-scale optimization, and in particular for neural network training. However, for nonsmooth and nonconvex objectives, few convergence guarantees…

Optimization and Control · Mathematics 2020-07-14 Vyacheslav Kungurtsev , Malcolm Egan , Bapi Chatterjee , Dan Alistarh

Stochastic Gradient Descent (SGD) is an important algorithm in machine learning. With constant learning rates, it is a stochastic process that, after an initial phase of convergence, generates samples from a stationary distribution. We show…

Machine Learning · Statistics 2017-09-12 Stephan Mandt , Matthew D. Hoffman , David M. Blei

Recently, Stochastic Gradient Descent (SGD) and its variants have become the dominant methods in the large-scale optimization of machine learning (ML) problems. A variety of strategies have been proposed for tuning the step sizes, ranging…

Machine Learning · Computer Science 2022-08-02 Xiaoyu Li

Momentum methods were originally introduced for their superiority to stochastic gradient descent (SGD) in deterministic settings with convex objective functions. However, despite their widespread application to deep neural networks -- a…

Machine Learning · Computer Science 2025-09-22 Kento Imaizumi , Hideaki Iiduka

Large-batch SGD is important for scaling training of deep neural networks. However, without fine-tuning hyperparameter schedules, the generalization of the model may be hampered. We propose to use batch augmentation: replicating instances…

Machine Learning · Computer Science 2019-01-29 Elad Hoffer , Tal Ben-Nun , Itay Hubara , Niv Giladi , Torsten Hoefler , Daniel Soudry

Neural networks are powerful parametric function approximators, while Gaussian processes (GPs) are nonparametric probabilistic models that place distributions over functions via kernel-defined correlations but become computationally…

Machine Learning · Computer Science 2025-12-09 Masoud Ataei , Vikas Dhiman , Mohammad Javad Khojasteh

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

Large-scale distributed training of deep neural networks results in models with worse generalization performance as a result of the increase in the effective mini-batch size. Previous approaches attempt to address this problem by varying…

Machine Learning · Computer Science 2020-02-17 Kazuki Osawa , Yohei Tsuji , Yuichiro Ueno , Akira Naruse , Chuan-Sheng Foo , Rio Yokota

Recent studies have demonstrated that noise in stochastic gradient descent (SGD) is closely related to generalization: A larger SGD noise, if not too large, results in better generalization. Since the covariance of the SGD noise is…

Machine Learning · Computer Science 2020-09-29 Takashi Mori , Masahito Ueda

A common way to speed up training of large convolutional networks is to add computational units. Training is then performed using data-parallel synchronous Stochastic Gradient Descent (SGD) with mini-batch divided between computational…

Computer Vision and Pattern Recognition · Computer Science 2017-09-15 Yang You , Igor Gitman , Boris Ginsburg

Algorithm-dependent generalization error bounds are central to statistical learning theory. A learning algorithm may use a large hypothesis space, but the limited number of iterations controls its model capacity and generalization error.…

Machine Learning · Computer Science 2017-07-20 Wenlong Mou , Liwei Wang , Xiyu Zhai , Kai Zheng

Low-precision training has become crucial for reducing the computational and memory costs of large-scale deep learning. However, quantizing gradients introduces magnitude shrinkage, which can change how stochastic gradient descent (SGD)…

Machine Learning · Computer Science 2026-01-09 Vincent-Daniel Yun

This paper proposes a thorough theoretical analysis of Stochastic Gradient Descent (SGD) with non-increasing step sizes. First, we show that the recursion defining SGD can be provably approximated by solutions of a time inhomogeneous…

Optimization and Control · Mathematics 2021-02-02 Xavier Fontaine , Valentin De Bortoli , Alain Durmus

In this paper, we first present an explanation regarding the common occurrence of spikes in the training loss when neural networks are trained with stochastic gradient descent (SGD). We provide evidence that the spikes in the training loss…

Machine Learning · Computer Science 2024-06-07 Libin Zhu , Chaoyue Liu , Adityanarayanan Radhakrishnan , Mikhail Belkin

Classical stochastic gradient methods are well suited for minimizing expected-value objective functions. However, they do not apply to the minimization of a nonlinear function involving expected values or a composition of two expected-value…

Machine Learning · Statistics 2014-11-17 Mengdi Wang , Ethan X. Fang , Han Liu

Stochastic gradient descent plays a fundamental role in nearly all applications of deep learning. However its ability to converge to a global minimum remains shrouded in mystery. In this paper we propose to study the behavior of the loss…

Machine Learning · Computer Science 2023-02-02 Mark Sandler , Andrey Zhmoginov , Max Vladymyrov , Nolan Miller

Stochastic gradient descent is a canonical tool for addressing stochastic optimization problems, and forms the bedrock of modern machine learning and statistics. In this work, we seek to balance the fact that attenuating step-size is…

Signal Processing · Electrical Eng. & Systems 2020-07-10 Zhan Gao , Alec Koppel , Alejandro Ribeiro

Research into optimisation for deep learning is characterised by a tension between the computational efficiency of first-order, gradient-based methods (such as SGD and Adam) and the theoretical efficiency of second-order, curvature-based…

Machine Learning · Computer Science 2024-06-17 Ross M. Clarke , José Miguel Hernández-Lobato

In this work, we propose to apply trust region optimization to deep reinforcement learning using a recently proposed Kronecker-factored approximation to the curvature. We extend the framework of natural policy gradient and propose to…

Machine Learning · Computer Science 2017-08-21 Yuhuai Wu , Elman Mansimov , Shun Liao , Roger Grosse , Jimmy Ba

Existing research shows that the batch size can seriously affect the performance of stochastic gradient descent~(SGD) based learning, including training speed and generalization ability. A larger batch size typically results in less…

Machine Learning · Statistics 2020-02-28 Shen-Yi Zhao , Yin-Peng Xie , Wu-Jun Li