English
Related papers

Related papers: A Study of Gradient Variance in Deep Learning

200 papers

Stochastic gradient descent (SGD) is widely believed to perform implicit regularization when used to train deep neural networks, but the precise manner in which this occurs has thus far been elusive. We prove that SGD minimizes an average…

Machine Learning · Computer Science 2018-01-17 Pratik Chaudhari , Stefano Soatto

A widely believed explanation for the remarkable generalization capacities of overparameterized neural networks is that the optimization algorithms used for training induce an implicit bias towards benign solutions. To grasp this…

Machine Learning · Computer Science 2025-12-19 Maria Matveev , Vit Fojtik , Hung-Hsu Chou , Gitta Kutyniok , Johannes Maly

In this work, we propose to progressively increase the training difficulty during learning a neural network model via a novel strategy which we call mini-batch trimming. This strategy makes sure that the optimizer puts its focus in the…

Computer Vision and Pattern Recognition · Computer Science 2021-10-26 Hannes Fassold

We study the effects of center initialization on the performance of a family of distributed gradient-based clustering algorithms introduced in [1], that work over connected networks of users. In the considered scenario, each user contains a…

Training instability in modern deep learning systems is frequently triggered by rare but extreme gradient-norm spikes, which can induce oversized parameter updates, corrupt optimizer state, and lead to slow recovery or divergence. Widely…

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

Theoretical analysis of the error landscape of deep neural networks has garnered significant interest in recent years. In this work, we theoretically study the importance of noise in the trajectories of gradient descent towards optimal…

Machine Learning · Computer Science 2018-07-24 Adepu Ravi Sankar , Vishwak Srinivasan , Vineeth N Balasubramanian

In this work we study generalization of neural networks in gradient-based meta-learning by analyzing various properties of the objective landscapes. We experimentally demonstrate that as meta-training progresses, the meta-test solutions,…

Machine Learning · Computer Science 2019-07-18 Simon Guiroy , Vikas Verma , Christopher Pal

In training neural networks, it is common practice to use partial gradients computed over batches, mostly very small subsets of the training set. This approach is motivated by the argument that such a partial gradient is close to the true…

Machine Learning · Computer Science 2024-11-25 Jan Spörer , Bernhard Bermeitinger , Tomas Hrycej , Niklas Limacher , Siegfried Handschuh

State-of-the-art training algorithms for deep learning models are based on stochastic gradient descent (SGD). Recently, many variations have been explored: perturbing parameters for better accuracy (such as in Extragradient), limiting SGD…

Machine Learning · Computer Science 2022-03-23 Amirkeivan Mohtashami , Martin Jaggi , Sebastian U. Stich

Stochastic gradient descent (SGD) with mini-batching is a standard tool in large-scale optimization, yet its theoretical properties under heavy-tailed gradient noise remain largely unexplored. In this paper we study SGD with increasing…

Probability · Mathematics 2026-05-11 Bartosz Glowacki , Rafal Kulik , Philippe Soulier

Large-batch stochastic gradient descent (SGD) is widely used for training in distributed deep learning because of its training-time efficiency, however, extremely large-batch SGD leads to poor generalization and easily converges to sharp…

Machine Learning · Computer Science 2019-06-27 Kosuke Haruki , Taiji Suzuki , Yohei Hamakawa , Takeshi Toda , Ryuji Sakai , Masahiro Ozawa , Mitsuhiro Kimura

As the state-of-the-art machine learning methods in many fields rely on larger datasets, storing datasets and training models on them become significantly more expensive. This paper proposes a training set synthesis technique for…

Computer Vision and Pattern Recognition · Computer Science 2021-03-09 Bo Zhao , Konda Reddy Mopuri , Hakan Bilen

Mini-batch stochastic gradient descent and variants thereof have become standard for large-scale empirical risk minimization like the training of neural networks. These methods are usually used with a constant batch size chosen by simple…

Machine Learning · Computer Science 2017-06-29 Lukas Balles , Javier Romero , Philipp Hennig

We consider machine learning applications that train a model by leveraging data distributed over a trusted network, where communication constraints can create a performance bottleneck. A number of recent approaches propose to overcome this…

Machine Learning · Computer Science 2021-09-10 Osama A. Hanna , Yahya H. Ezzeldin , Christina Fragouli , Suhas Diggavi

Deep neural networks (DNNs) for supervised learning can be viewed as a pipeline of a feature extractor (i.e. last hidden layer) and a linear classifier (i.e. output layer) that is trained jointly with stochastic gradient descent (SGD). In…

Machine Learning · Computer Science 2020-02-28 Xiangrui Li , Deng Pan , Xin Li , Dongxiao Zhu

Improving performance of deep learning models and reducing their training times are ongoing challenges in deep neural networks. There are several approaches proposed to address these challenges one of which is to increase the depth of the…

Machine Learning · Computer Science 2020-06-20 Sunitha Basodi , Chunyan Ji , Haiping Zhang , Yi Pan

Variational approaches to disparity estimation typically use a linearised brightness constancy constraint, which only applies in smooth regions and over small distances. Accordingly, current variational approaches rely on a schedule to…

Image and Video Processing · Electrical Eng. & Systems 2024-05-28 James L. Gray , Aous T. Naman , David S. Taubman

Stochastic gradient descent (SGD) with momentum is widely used for training modern deep learning architectures. While it is well-understood that using momentum can lead to faster convergence rate in various settings, it has also been…

Machine Learning · Computer Science 2022-07-14 Samy Jelassi , Yuanzhi Li

Increasing the mini-batch size for stochastic gradient descent offers significant opportunities to reduce wall-clock training time, but there are a variety of theoretical and systems challenges that impede the widespread success of this…

‹ Prev 1 3 4 5 6 7 10 Next ›