中文
相关论文

相关论文: Non-Gaussianity of Stochastic Gradient Noise

200 篇论文

The stochastic gradient descent (SGD) method is most widely used for deep neural network (DNN) training. However, the method does not always converge to a flat minimum of the loss surface that can demonstrate high generalization capability.…

机器学习 · 计算机科学 2020-09-08 Wonyong Sung , Iksoo Choi , Jinhwan Park , Seokhyun Choi , Sungho Shin

In this paper, we investigate the limiting behavior of a continuous-time counterpart of the Stochastic Gradient Descent (SGD) algorithm applied to two-layer overparameterized neural networks, as the number or neurons (ie, the size of the…

机器学习 · 统计学 2020-07-15 Valentin De Bortoli , Alain Durmus , Xavier Fontaine , Umut Simsekli

The noise in stochastic gradient descent (SGD), caused by minibatch sampling, is poorly understood despite its practical importance in deep learning. This work presents the first systematic study of the SGD noise and fluctuations close to a…

机器学习 · 计算机科学 2022-03-09 Liu Ziyin , Kangqiao Liu , Takashi Mori , Masahito Ueda

With an increasing demand for training powers for deep learning algorithms and the rapid growth of computation resources in data centers, it is desirable to dynamically schedule different distributed deep learning tasks to maximize resource…

机器学习 · 计算机科学 2019-05-03 Haibin Lin , Hang Zhang , Yifei Ma , Tong He , Zhi Zhang , Sheng Zha , Mu Li

SGD is the widely adopted method to train CNN. Conceptually it approximates the population with a randomly sampled batch; then it evenly trains batches by conducting a gradient update on every batch in an epoch. In this paper, we…

机器学习 · 计算机科学 2017-03-29 Linnan Wang , Yi Yang , Martin Renqiang Min , Srimat Chakradhar

We analyze a batched variant of Stochastic Gradient Descent (SGD) with weighted sampling distribution for smooth and non-smooth objective functions. We show that by distributing the batches computationally, a significant speedup in the…

数值分析 · 数学 2017-03-02 Deanna Needell , Rachel Ward

We present an approach for efficiently training Gaussian Mixture Model (GMM) by Stochastic Gradient Descent (SGD) with non-stationary, high-dimensional streaming data. Our training scheme does not require data-driven parameter…

机器学习 · 计算机科学 2021-07-05 Alexander Gepperth , Benedikt Pfülb

Deep neural networks achieve stellar generalisation even when they have enough parameters to easily fit all their training data. We study this phenomenon by analysing the dynamics and the performance of over-parameterised two-layer neural…

机器学习 · 统计学 2022-03-28 Sebastian Goldt , Madhu S. Advani , Andrew M. Saxe , Florent Krzakala , Lenka Zdeborová

Stochastic Gradient Langevin Dynamics (SGLD) is a popular variant of Stochastic Gradient Descent, where properly scaled isotropic Gaussian noise is added to an unbiased estimate of the gradient at each iteration. This modest change allows…

机器学习 · 计算机科学 2017-06-06 Maxim Raginsky , Alexander Rakhlin , Matus Telgarsky

The performance of mini-batch stochastic gradient descent (SGD) strongly depends on setting the batch size and learning rate to minimize the empirical loss in training the deep neural network. In this paper, we present theoretical analyses…

机器学习 · 计算机科学 2025-02-17 Hikaru Umeda , Hideaki Iiduka

Machine learning, especially deep neural networks, has been rapidly developed in fields including computer vision, speech recognition and reinforcement learning. Although Mini-batch SGD is one of the most popular stochastic optimization…

机器学习 · 计算机科学 2019-03-12 Xinyu Peng , Li Li , Fei-Yue Wang

We investigate how the final parameters found by stochastic gradient descent are influenced by over-parameterization. We generate families of models by increasing the number of channels in a base network, and then perform a large…

机器学习 · 计算机科学 2019-05-10 Daniel S. Park , Jascha Sohl-Dickstein , Quoc V. Le , Samuel L. Smith

Classical stochastic gradient methods for optimization rely on noisy gradient approximations that become progressively less accurate as iterates approach a solution. The large noise and small signal in the resulting gradients makes it…

机器学习 · 计算机科学 2017-04-10 Soham De , Abhay Yadav , David Jacobs , Tom Goldstein

The ability to train large-scale neural networks has resulted in state-of-the-art performance in many areas of computer vision. These results have largely come from computational break throughs of two forms: model parallelism, e.g. GPU…

计算机视觉与模式识别 · 计算机科学 2013-12-24 Thomas Paine , Hailin Jin , Jianchao Yang , Zhe Lin , Thomas Huang

Stochastic variance-reduced gradient (SVRG) is a classical optimization method. Although it is theoretically proved to have better convergence performance than stochastic gradient descent (SGD), the generalization performance of SVRG…

机器学习 · 统计学 2019-08-20 Hao Jin , Dachao Lin , Zhihua Zhang

An important question in deep learning is how higher-order optimization methods affect generalization. In this work, we analyze a stochastic Gauss-Newton (SGN) method with Levenberg-Marquardt damping and mini-batch sampling for training…

机器学习 · 计算机科学 2025-11-13 Semih Cayci

Synchronous stochastic gradient descent (SGD) is the most common method used for distributed training of deep learning models. In this algorithm, each worker shares its local gradients with others and updates the parameters using the…

机器学习 · 计算机科学 2020-09-22 Negar Foroutan Eghlidi , Martin Jaggi

Deep neural networks achieve stellar generalisation on a variety of problems, despite often being large enough to easily fit all their training data. Here we study the generalisation dynamics of two-layer neural networks in a…

机器学习 · 统计学 2019-06-21 Sebastian Goldt , Madhu S. Advani , Andrew M. Saxe , Florent Krzakala , Lenka Zdeborová

The most straightforward method to accelerate Stochastic Gradient Descent (SGD) computation is to distribute the randomly selected batch of inputs over multiple processors. To keep the distributed processors fully utilized requires…

机器学习 · 计算机科学 2020-01-06 Zhewei Yao , Amir Gholami , Daiyaan Arfeen , Richard Liaw , Joseph Gonzalez , Kurt Keutzer , Michael Mahoney

Past research has indicated that the covariance of the Stochastic Gradient Descent (SGD) error done via minibatching plays a critical role in determining its regularization and escape from low potential points. Motivated by some new…

机器学习 · 统计学 2023-03-02 Riddhiman Bhattacharya , Tiefeng Jiang