English
Related papers

Related papers: Dynamically Adjusting Transformer Batch Size by Mo…

200 papers

In current deep learning tasks, Adam style optimizers such as Adam, Adagrad, RMSProp, Adafactor, and Lion have been widely used as alternatives to SGD style optimizers. These optimizers typically update model parameters using the sign of…

Machine Learning · Computer Science 2024-10-29 Shuaipeng Li , Penghao Zhao , Hailin Zhang , Xingwu Sun , Hao Wu , Dian Jiao , Weiyan Wang , Chengjun Liu , Zheng Fang , Jinbao Xue , Yangyu Tao , Bin Cui , Di Wang

In this work, we investigate the effect of momentum on the optimisation trajectory of gradient descent. We leverage a continuous-time approach in the analysis of momentum gradient descent with step size $\gamma$ and momentum parameter…

Machine Learning · Computer Science 2024-03-11 Hristo Papazov , Scott Pesme , Nicolas Flammarion

The convergence of stochastic gradient descent is highly dependent on the step-size, especially on non-convex problems such as neural network training. Step decay step-size schedules (constant and then cut) are widely used in practice…

Optimization and Control · Mathematics 2021-02-19 Xiaoyu Wang , Sindri Magnússon , Mikael Johansson

Batch Normalization (BN) has become a cornerstone of deep learning across diverse architectures, appearing to help optimization as well as generalization. While the idea makes intuitive sense, theoretical analysis of its effectiveness has…

Machine Learning · Computer Science 2018-12-11 Sanjeev Arora , Zhiyuan Li , Kaifeng Lyu

The practical performance of online stochastic gradient descent algorithms is highly dependent on the chosen step size, which must be tediously hand-tuned in many applications. The same is true for more advanced variants of stochastic…

Optimization and Control · Mathematics 2015-11-10 Pierre-Yves Massé , Yann Ollivier

For infinitesimal learning rates, stochastic gradient descent (SGD) follows the path of gradient flow on the full batch loss function. However moderately large learning rates can achieve higher test accuracies, and this generalization…

Machine Learning · Computer Science 2021-01-29 Samuel L. Smith , Benoit Dherin , David G. T. Barrett , Soham De

A number of optimization approaches have been proposed for optimizing nonconvex objectives (e.g. deep learning models), such as batch gradient descent, stochastic gradient descent and stochastic variance reduced gradient descent. Theory…

Machine Learning · Computer Science 2019-05-15 Jia Bi , Steve R. Gunn

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

This paper introduces a novel approach to enhance the performance of the stochastic gradient descent (SGD) algorithm by incorporating a modified decay step size based on $\frac{1}{\sqrt{t}}$. The proposed step size integrates a logarithmic…

Machine Learning · Computer Science 2023-09-06 M. Soheil Shamaee , S. Fathi Hafshejani

Although deep learning has produced dazzling successes for applications of image, speech, and video processing in the past few years, most trainings are with suboptimal hyper-parameters, requiring unnecessarily long training times. Setting…

Machine Learning · Computer Science 2018-04-25 Leslie N. Smith

A variety of widely used optimization methods like SignSGD and Muon can be interpreted as instances of steepest descent under different norm-induced geometries. In this work, we study the implicit bias of mini-batch stochastic steepest…

Machine Learning · Computer Science 2026-02-13 Jichu Li , Xuan Tang , Difan Zou

The accuracy of deep neural networks is significantly affected by how well mini-batches are constructed during the training step. In this paper, we propose a novel adaptive batch selection algorithm called Recency Bias that exploits the…

Machine Learning · Computer Science 2020-12-24 Hwanjun Song , Minseok Kim , Sundong Kim , Jae-Gil Lee

This paper considers unconstrained convex optimization problems with time-varying objective functions. We propose algorithms with a discrete time-sampling scheme to find and track the solution trajectory based on prediction and correction…

Information Theory · Computer Science 2017-09-18 Andrea Simonetto , Aryan Mokhtari , Alec Koppel , Geert Leus , Alejandro Ribeiro

Neural network training is commonly accelerated by using multiple synchronized workers to compute gradient updates in parallel. Asynchronous methods remove synchronization overheads and improve hardware utilization at the cost of…

Machine Learning · Computer Science 2020-07-13 Abhinav Venigalla , Atli Kosson , Vitaliy Chiley , Urs Köster

Batch Normalization (BatchNorm) is commonly used in Convolutional Neural Networks (CNNs) to improve training speed and stability. However, there is still limited consensus on why this technique is effective. This paper uses concepts from…

Neural and Evolutionary Computing · Computer Science 2021-06-02 Elaina Chai , Mert Pilanci , Boris Murmann

We propose \textit{Meta-Regularization}, a novel approach for the adaptive choice of the learning rate in first-order gradient descent methods. Our approach modifies the objective function by adding a regularization term on the learning…

Machine Learning · Computer Science 2021-04-13 Guangzeng Xie , Hao Jin , Dachao Lin , Zhihua Zhang

Interpreting gradient methods as fixed-point iterations, we provide a detailed analysis of those methods for minimizing convex objective functions. Due to their conceptual and algorithmic simplicity, gradient methods are widely used in…

Machine Learning · Statistics 2017-08-16 Alexander Jung

Commonly used optimization algorithms often show a trade-off between good generalization and fast training times. For instance, stochastic gradient descent (SGD) tends to have good generalization; however, adaptive gradient methods have…

Machine Learning · Computer Science 2023-06-14 Aditya Cowsik , Tankut Can , Paolo Glorioso

We introduce a general method for improving the convergence rate of gradient-based optimizers that is easy to implement and works well in practice. We demonstrate the effectiveness of the method in a range of optimization problems by…

Machine Learning · Computer Science 2018-08-23 Atilim Gunes Baydin , Robert Cornish , David Martinez Rubio , Mark Schmidt , Frank Wood

In recent years, large pre-trained Transformer-based language models have led to dramatic improvements in many natural language understanding tasks. To train these models with increasing sizes, many neural network practitioners attempt to…

Machine Learning · Computer Science 2022-02-01 Minjia Zhang , Niranjan Uma Naresh , Yuxiong He