English
Related papers

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

200 papers

Mini-batch gradient descent based methods are the de facto algorithms for training neural network architectures today. We introduce a mini-batch selection strategy based on submodular function maximization. Our novel submodular formulation…

Machine Learning · Computer Science 2019-06-21 K J Joseph , Vamshi Teja R , Krishnakant Singh , Vineeth N Balasubramanian

In this paper, we study the finite-sum convex optimization problem focusing on the general convex case. Recently, the study of variance reduced (VR) methods and their accelerated variants has made exciting progress. However, the step size…

Optimization and Control · Mathematics 2022-01-31 Zijian Liu , Ta Duy Nguyen , Alina Ene , Huy L. Nguyen

In several recently proposed stochastic optimization methods (e.g. RMSProp, Adam, Adadelta), parameter updates are scaled by the inverse square roots of exponential moving averages of squared past gradients. Maintaining these per-parameter…

Machine Learning · Computer Science 2018-04-13 Noam Shazeer , Mitchell Stern

Scalable algorithms of posterior approximation allow Bayesian nonparametrics such as Dirichlet process mixture to scale up to larger dataset at fractional cost. Recent algorithms, notably the stochastic variational inference performs local…

Machine Learning · Computer Science 2025-02-25 Kart-Leong Lim , Xudong Jiang

Increasing the batch size during training -- a ''batch ramp'' -- is a promising strategy to accelerate large language model pretraining. While for SGD, doubling the batch size can be equivalent to halving the learning rate, the optimal…

Machine Learning · Computer Science 2025-10-17 Alexandru Meterez , Depen Morwani , Jingfeng Wu , Costin-Andrei Oncescu , Cengiz Pehlevan , Sham Kakade

In neural network training, RMSProp and Adam remain widely favoured optimisation algorithms. One of the keys to their performance lies in selecting the correct step size, which can significantly influence their effectiveness. Additionally,…

Machine Learning · Computer Science 2024-04-05 Alokendu Mazumder , Rishabh Sabharwal , Manan Tayal , Bhartendu Kumar , Punit Rathore

Synchronous strategies with data parallelism, such as the Synchronous StochasticGradient Descent (S-SGD) and the model averaging methods, are widely utilizedin distributed training of Deep Neural Networks (DNNs), largely owing to itseasy…

Machine Learning · Computer Science 2022-11-04 Qing Ye , Yuhao Zhou , Mingjia Shi , Yanan Sun , Jiancheng Lv

In machine learning applications, it is well known that carefully designed learning rate (step size) schedules can significantly improve the convergence of commonly used first-order optimization algorithms. Therefore how to set step size…

Optimization and Control · Mathematics 2023-10-19 Xiaoyu Wang , Mikael Johansson , Tong Zhang

We study the effect of mini-batching on the loss landscape of deep neural networks using spiked, field-dependent random matrix theory. We demonstrate that the magnitude of the extremal values of the batch Hessian are larger than those of…

Machine Learning · Statistics 2021-11-08 Diego Granziol , Stefan Zohren , Stephen Roberts

This work is substituted by the paper in arXiv:2011.14066. Stochastic gradient descent is the de facto algorithm for training deep neural networks (DNNs). Despite its popularity, it still requires fine tuning in order to achieve its best…

Machine Learning · Statistics 2020-12-02 Vatsal Shah , Anastasios Kyrillidis , Sujay Sanghavi

This paper studies some asymptotic properties of adaptive algorithms widely used in optimization and machine learning, and among them Adagrad and Rmsprop, which are involved in most of the blackbox deep learning algorithms. Our setup is the…

Machine Learning · Statistics 2020-12-15 Sébastien Gadat , Ioana Gavra

In this paper, we develop a new accelerated stochastic gradient method for efficiently solving the convex regularized empirical risk minimization problem in mini-batch settings. The use of mini-batches is becoming a golden standard in the…

Optimization and Control · Mathematics 2017-09-20 Tomoya Murata , Taiji Suzuki

Large-batch training has been essential in leveraging large-scale datasets and models in deep learning. While it is computationally beneficial to use large batch sizes, it often requires a specially designed learning rate (LR) schedule to…

Machine Learning · Computer Science 2021-07-14 Chiheon Kim , Saehoon Kim , Jongmin Kim , Donghoon Lee , Sungwoong Kim

We propose a new per-layer adaptive step-size procedure for stochastic first-order optimization methods for minimizing empirical loss functions in deep learning, eliminating the need for the user to tune the learning rate (LR). The proposed…

Machine Learning · Computer Science 2023-07-07 Achraf Bahamou , Donald Goldfarb

The adaptive gradient online learning method known as AdaGrad has seen widespread use in the machine learning community in stochastic and adversarial online learning problems and more recently in deep learning methods. The method's…

Machine Learning · Computer Science 2016-10-05 Nishant A. Mehta , Alistair Rendell , Anish Varghese , Christfried Webers

The choice of hyper-parameters affects the performance of neural models. While much previous research (Sutskever et al., 2013; Duchi et al., 2011; Kingma and Ba, 2015) focuses on accelerating convergence and reducing the effects of the…

Computation and Language · Computer Science 2020-05-06 Hongfei Xu , Josef van Genabith , Deyi Xiong , Qiuhui Liu

This paper presents a gradient-informed fine-tuning method for large language models under few-shot conditions. The goal is to enhance task adaptability and training stability when data is limited. The method builds on a base loss function…

Computation and Language · Computer Science 2025-06-03 Hongye Zheng , Yichen Wang , Ray Pan , Guiran Liu , Binrong Zhu , Hanlu Zhang

Recent results in non-convex stochastic optimization demonstrate the convergence of popular adaptive algorithms (e.g., AdaGrad) under the $(L_0, L_1)$-smoothness condition, but the rate of convergence is a higher-order polynomial in terms…

Machine Learning · Computer Science 2025-05-09 Michael Crawshaw , Mingrui Liu

This paper presents a methodology for selecting the mini-batch size that minimizes Stochastic Gradient Descent (SGD) learning time for single and multiple learner problems. By decoupling algorithmic analysis issues from hardware and…

Machine Learning · Computer Science 2019-11-18 Michael P. Perrone , Haidar Khan , Changhoan Kim , Anastasios Kyrillidis , Jerry Quinn , Valentina Salapura

It is common practice to decay the learning rate. Here we show one can usually obtain the same learning curve on both training and test sets by instead increasing the batch size during training. This procedure is successful for stochastic…

Machine Learning · Computer Science 2018-02-27 Samuel L. Smith , Pieter-Jan Kindermans , Chris Ying , Quoc V. Le