English
Related papers

Related papers: The Disharmony between BN and ReLU Causes Gradient…

200 papers

This paper first answers the question "why do the two most powerful techniques Dropout and Batch Normalization (BN) often lead to a worse performance when they are combined together?" in both theoretical and statistical aspects.…

Machine Learning · Computer Science 2018-01-17 Xiang Li , Shuo Chen , Xiaolin Hu , Jian Yang

Recurrent neural networks (RNNs) are wide-spread machine learning tools for modeling sequential and time series data. They are notoriously hard to train because their loss gradients backpropagated in time tend to saturate or diverge during…

Machine Learning · Computer Science 2022-10-10 Jonas M. Mikhaeil , Zahra Monfared , Daniel Durstewitz

We study the problem of learning one-hidden-layer neural networks with Rectified Linear Unit (ReLU) activation function, where the inputs are sampled from standard Gaussian distribution and the outputs are generated from a noisy teacher…

Machine Learning · Statistics 2018-06-21 Xiao Zhang , Yaodong Yu , Lingxiao Wang , Quanquan Gu

Neural networks are powerful functions with widespread use, but the theoretical behaviour of these functions is not fully understood. Creating deep neural networks by stacking many layers has achieved exceptional performance in many…

Machine Learning · Computer Science 2024-08-16 Cameron Jakub , Mihai Nica

Deep learning models are effective for sequential data modeling, yet commonly used activation functions such as ReLU, LeakyReLU, and PReLU often exhibit gradient instability when applied to noisy, non-stationary financial time series. This…

Machine Learning · Computer Science 2026-01-26 George Awiakye-Marfo , Elijah Agbosu , Victoria Mawuena Barns , Samuel Asante Gyamerah

Numerous theories of learning propose to prevent the gradient from exponential growth with depth or time, to stabilize and improve training. Typically, these analyses are conducted on feed-forward fully-connected neural networks or simple…

Machine Learning · Computer Science 2024-01-08 Luca Herranz-Celotti , Jean Rouat

The instability of Generative Adversarial Network (GAN) training has frequently been attributed to gradient descent. Consequently, recent methods have aimed to tailor the models and training procedures to stabilise the discrete updates. In…

Activation functions play a critical role in deep neural networks by shaping gradient flow, optimization stability, and generalization. While ReLU remains widely used due to its simplicity, it suffers from gradient sparsity and dead-neuron…

Machine Learning · Computer Science 2025-12-03 Ashkan Shakarami , Yousef Yeganeh , Azade Farshad , Lorenzo Nicolè , Stefano Ghidoni , Nassir Navab

Injecting noise within gradient descent has several desirable features, such as smoothing and regularizing properties. In this paper, we investigate the effects of injecting noise before computing a gradient step. We demonstrate that small…

Machine Learning · Computer Science 2023-01-24 Antonio Orvieto , Anant Raj , Hans Kersting , Francis Bach

Binary neural networks improve computationally efficiency of deep models with a large margin. However, there is still a performance gap between a successful full-precision training and binary training. We bring some insights about why this…

Machine Learning · Computer Science 2020-04-22 Xinlin Li , Vahid Partovi Nia

This work studies the behavior of shallow ReLU networks trained with the logistic loss via gradient descent on binary classification data where the underlying data distribution is general, and the (optimal) Bayes risk is not necessarily…

Machine Learning · Computer Science 2021-11-05 Ziwei Ji , Justin D. Li , Matus Telgarsky

In many numerical simulations stochastic gradient descent (SGD) type optimization methods perform very effectively in the training of deep neural networks (DNNs) but till this day it remains an open problem of research to provide a…

Machine Learning · Computer Science 2023-06-26 Martin Hutzenthaler , Arnulf Jentzen , Katharina Pohl , Adrian Riekert , Luca Scarpa

Implementation of quantized neural networks on computing hardware leads to considerable speed up and memory saving. However, quantized deep networks are difficult to train and batch~normalization (BatchNorm) layer plays an important role in…

Machine Learning · Computer Science 2020-04-30 Eyyüb Sari , Vahid Partovi Nia

We show that deep reinforcement learning algorithms can retain their ability to learn without resetting network parameters in settings where the number of gradient updates greatly exceeds the number of environment samples by combatting…

Machine Learning · Computer Science 2024-08-06 Marcel Hussing , Claas Voelcker , Igor Gilitschenski , Amir-massoud Farahmand , Eric Eaton

The Rectified Power Unit (RePU) activation function, a differentiable generalization of the Rectified Linear Unit (ReLU), has shown promise in constructing neural networks due to its smoothness properties. However, deep RePU networks often…

Machine Learning · Computer Science 2026-02-10 Taeyoung Kim , Myungjoo Kang

Overparameterized ML models, including neural networks, typically induce underdetermined training objectives with multiple global minima. The implicit bias refers to the limiting global minimum that is attained by a common optimization…

Machine Learning · Statistics 2026-03-06 Kuo-Wei Lai , Guanghui Wang , Molei Tao , Vidya Muthukumar

In order to alleviate the notorious mode collapse phenomenon in generative adversarial networks (GANs), we propose a novel training method of GANs in which certain fake samples are considered as real ones during the training process. This…

Machine Learning · Computer Science 2020-03-17 Song Tao , Jia Wang

In this paper we address the issue of output instability of deep neural networks: small perturbations in the visual input can significantly distort the feature embeddings and output of a neural network. Such instability affects many deep…

Computer Vision and Pattern Recognition · Computer Science 2016-04-18 Stephan Zheng , Yang Song , Thomas Leung , Ian Goodfellow

In active learning, the size and complexity of the training dataset changes over time. Simple models that are well specified by the amount of data available at the start of active learning might suffer from bias as more points are actively…

Machine Learning · Computer Science 2022-05-05 Chelsea Murray , James U. Allingham , Javier Antorán , José Miguel Hernández-Lobato

The training of artificial neural networks (ANNs) with rectified linear unit (ReLU) activation via gradient descent (GD) type optimization schemes is nowadays a common industrially relevant procedure. Till this day in the scientific…

Machine Learning · Computer Science 2023-04-13 Simon Eberle , Arnulf Jentzen , Adrian Riekert , Georg S. Weiss