English
Related papers

Related papers: A Mechanism Study of Delayed Loss Spikes in Batch-…

200 papers

Recently, deep learning is considered to optimize the end-to-end performance of digital communication systems. The promise of learning a digital communication scheme from data is attractive, since this makes the scheme adaptable and…

Signal Processing · Electrical Eng. & Systems 2021-07-19 Simon Bos , Evgenii Vinogradov , Sofie Pollin

Normalization techniques play an important role in supporting efficient and often more effective training of deep neural networks. While conventional methods explicitly normalize the activations, we suggest to add a loss term instead. This…

Machine Learning · Computer Science 2018-11-22 Etai Littwin , Lior Wolf

Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates…

Machine Learning · Computer Science 2015-03-03 Sergey Ioffe , Christian Szegedy

Understanding the dynamics of neural networks in different width regimes is crucial for improving their training and performance. We present an exact solution for the learning dynamics of a one-hidden-layer linear network, with…

Machine Learning · Computer Science 2025-02-24 Yizhou Xu , Liu Ziyin

Delay differential equations (DDEs) with large delays play a pivotal role in understanding stability and bifurcations in systems ranging from neural networks to laser dynamics. While prior work has extensively studied DDEs with discrete…

Dynamical Systems · Mathematics 2025-09-09 Isam Al-Darabsah , Sue Ann Campbell , Bootan Rahman

Batch normalization (BN) is a technique to normalize activations in intermediate layers of deep neural networks. Its tendency to improve accuracy and speed up training have established BN as a favorite technique in deep learning. Yet,…

Machine Learning · Computer Science 2018-12-03 Johan Bjorck , Carla Gomes , Bart Selman , Kilian Q. Weinberger

Training neural networks is an optimization problem, and finding a decent set of parameters through gradient descent can be a difficult task. A host of techniques has been developed to aid this process before and during the training phase.…

Machine Learning · Computer Science 2020-08-19 Divya Gaur , Joachim Folz , Andreas Dengel

Time series forecasting has become a critical task due to its high practicality in real-world applications such as traffic, energy consumption, economics and finance, and disease analysis. Recent deep-learning-based approaches have shown…

Machine Learning · Computer Science 2023-05-30 Youngin Cho , Daejin Kim , Dongmin Kim , Mohammad Azam Khan , Jaegul Choo

Deep Neural Networks (DNNs) are becoming integral components of real world services relied upon by millions of users. Unfortunately, architects of these systems can find it difficult to ensure reliable performance as irrelevant details like…

Machine Learning · Computer Science 2023-05-22 Arghya Datta , Subhrangshu Nandi , Jingcheng Xu , Greg Ver Steeg , He Xie , Anoop Kumar , Aram Galstyan

Recently there has been a surge of interest in understanding implicit regularization properties of iterative gradient-based optimization algorithms. In this paper, we study the statistical guarantees on the excess risk achieved by…

Machine Learning · Statistics 2020-08-28 Tomas Vaškevičius , Varun Kanade , Patrick Rebeschini

The success of denoising diffusion models raises important questions regarding their generalisation behaviour, particularly in high-dimensional settings. Notably, it has been shown that when training and sampling are performed perfectly,…

Machine Learning · Statistics 2025-07-08 Tyler Farghly , Patrick Rebeschini , George Deligiannidis , Arnaud Doucet

Underpinning the past decades of work on the design, initialization, and optimization of neural networks is a seemingly innocuous assumption: that the network is trained on a \textit{stationary} data distribution. In settings where this…

Machine Learning · Computer Science 2024-03-01 Clare Lyle , Zeyu Zheng , Khimya Khetarpal , Hado van Hasselt , Razvan Pascanu , James Martens , Will Dabney

Covariate shift has been shown to sharply degrade both predictive accuracy and the calibration of uncertainty estimates for deep learning models. This is worrying, because covariate shift is prevalent in a wide range of real world…

Machine Learning · Computer Science 2021-01-18 Zachary Nado , Shreyas Padhy , D. Sculley , Alexander D'Amour , Balaji Lakshminarayanan , Jasper Snoek

This paper proposes a supervisory control structure for networked systems with time-varying delays. The control structure, in which a supervisor triggers the most appropriate controller from a multi-controller unit, aims at improving the…

Systems and Control · Computer Science 2013-03-28 Burak Demirel , Corentin Briat , Mikael Johansson

Batch Normalization (BN) is extensively employed in various network architectures by performing standardization within mini-batches. A full understanding of the process has been a central target in the deep learning communities. Unlike…

Computer Vision and Pattern Recognition · Computer Science 2020-03-30 Lei Huang , Lei Zhao , Yi Zhou , Fan Zhu , Li Liu , Ling Shao

In recent years, new regularization methods based on (deep) neural networks have shown very promising empirical performance for the numerical solution of ill-posed problems, e.g., in medical imaging and imaging science. Due to the…

Numerical Analysis · Mathematics 2024-06-07 Tim Jahn , Bangti Jin

The time elapsed model describes the firing activity of an homogeneous assembly of neurons thanks to the distribution of times elapsed since the last discharge. It gives a mathematical description of the probability density of neurons…

Analysis of PDEs · Mathematics 2011-09-16 Khashayar Pakdaman , Benoît Perthame , Delphine Salort

In gradient descent dynamics of neural networks, the top eigenvalue of the loss Hessian (sharpness) displays a variety of robust phenomena throughout training. This includes early time regimes where the sharpness may decrease during early…

Machine Learning · Computer Science 2025-02-17 Dayal Singh Kalra , Tianyu He , Maissam Barkeshli

In this article, we focus on extending the notion of lattice linearity to self-stabilizing programs. Lattice linearity allows a node to execute its actions with old information about the state of other nodes and still preserve correctness.…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-10-19 Arya Tanmay Gupta , Sandeep S Kulkarni

Time delayed feedback control is one of the most successful methods to discover dynamically unstable features of a dynamical system in an experiment. This approach feeds back only terms that depend on the difference between the current…

Dynamical Systems · Mathematics 2016-04-26 Jan Sieber