English
Related papers

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

200 papers

It is known that training deep neural networks, in particular, deep convolutional networks, with aggressively reduced numerical precision is challenging. The stochastic gradient descent algorithm becomes unstable in the presence of noisy…

Machine Learning · Computer Science 2016-07-11 Darryl D. Lin , Sachin S. Talathi

Traditional algorithms to optimize artificial neural networks when confronted with a supervised learning task are usually exploitation-type relaxational dynamics such as gradient descent (GD). Here, we explore the dynamics of the neural…

Machine Learning · Computer Science 2026-03-10 Pedro Jiménez-González , Miguel C. Soriano , Lucas Lacasa

Modern deep learning models with great expressive power can be trained to overfit the training data but still generalize well. This phenomenon is referred to as \textit{benign overfitting}. Recently, a few studies have attempted to…

Machine Learning · Computer Science 2023-11-07 Yiwen Kou , Zixiang Chen , Yuanzhou Chen , Quanquan Gu

Gradient dynamics play a central role in determining the stability and generalization of deep neural networks. In this work, we provide an empirical analysis of how variance and standard deviation of gradients evolve during training,…

Machine Learning · Computer Science 2025-09-09 Vincent-Daniel Yun

Despite exceptional achievements, training neural networks remains computationally expensive and is often plagued by instabilities that can degrade convergence. While learning rate schedules can help mitigate these issues, finding optimal…

Machine Learning · Computer Science 2026-03-30 Benoit Dherin , Benny Avelin , Anders Karlsson , Hanna Mazzawi , Javier Gonzalvo , Michael Munn

In addition to high accuracy, robustness is becoming increasingly important for machine learning models in various applications. Recently, much research has been devoted to improving the model robustness by training with noise…

Machine Learning · Computer Science 2021-03-30 Kun-Peng Ning , Lue Tao , Songcan Chen , Sheng-Jun Huang

Deep reinforcement learning (RL) agents frequently suffer from neuronal activity loss, which impairs their ability to adapt to new data and learn continually. A common method to quantify and address this issue is the tau-dormant neuron…

Machine Learning · Computer Science 2026-02-03 Jiashun Liu , Zihao Wu , Johan Obando-Ceron , Pablo Samuel Castro , Aaron Courville , Ling Pan

Deep neural networks are a promising approach towards multi-task learning because of their capability to leverage knowledge across domains and learn general purpose representations. Nevertheless, they can fail to live up to these promises…

Machine Learning · Computer Science 2019-12-17 Mihai Suteu , Yike Guo

Backpropagation (BP) remains the dominant and most successful method for training parameters of deep neural network models. However, BP relies on two computationally distinct phases, does not provide a satisfactory explanation of biological…

Machine Learning · Computer Science 2025-11-12 Sander Dalm , Marcel van Gerven , Nasir Ahmad

Training a neural network with the gradient descent algorithm gives rise to a discrete-time nonlinear dynamical system. Consequently, behaviors that are typically observed in these systems emerge during training, such as convergence to an…

Machine Learning · Computer Science 2018-10-10 Kamil Nar , S. Shankar Sastry

Our theoretical understanding of neural networks is lagging behind their empirical success. One of the important unexplained phenomena is why and how, during the process of training with gradient descent, the theoretical capacity of neural…

Machine Learning · Computer Science 2026-05-08 Hannah Pinson

During long-duration Large Language Model (LLM) training runs the gradient norm increases rapidly near the end of training. In this short note, we show that this increase is due to an unintended interaction between weight decay,…

Machine Learning · Computer Science 2025-06-11 Aaron Defazio

In this work, we study the evolution of the loss Hessian across many classification tasks in order to understand the effect the curvature of the loss has on the training dynamics. Whereas prior work has focused on how different learning…

This study introduces a novel activation function, characterized by a dynamic slope that adjusts throughout the training process, aimed at enhancing adaptability and performance in deep neural networks for computer vision tasks. The…

Computer Vision and Pattern Recognition · Computer Science 2024-08-20 Archisman Chakraborti , Bidyut B Chaudhuri

This paper studies the problem of training a two-layer ReLU network for binary classification using gradient flow with small initialization. We consider a training dataset with well-separated input vectors: Any pair of input data with the…

Machine Learning · Computer Science 2024-03-26 Hancheng Min , Enrique Mallada , René Vidal

Understanding implicit bias of gradient descent for generalization capability of ReLU networks has been an important research topic in machine learning research. Unfortunately, even for a single ReLU neuron trained with the square loss, it…

Machine Learning · Computer Science 2022-06-14 Sangmin Lee , Byeongsu Sim , Jong Chul Ye

A key challenge in modern deep learning theory is to explain the remarkable success of gradient-based optimization methods when training large-scale, complex deep neural networks. Though linear convergence of such methods has been proved…

Machine Learning · Computer Science 2025-09-30 Yash Jakhmola

Learning and decision making in the brain are key processes critical to survival, and yet are processes implemented by non-ideal biological building blocks which can impose significant error. We explore quantitatively how the brain might…

Neurons and Cognition · Quantitative Biology 2011-04-19 Jake Bouvrie , Jean-Jacques Slotine

Deep neural networks often produce overconfident predictions, undermining their reliability in safety-critical applications. This miscalibration is further exacerbated under distribution shift, where test data deviates from the training…

Computer Vision and Pattern Recognition · Computer Science 2025-08-28 Yilin Zhang , Cai Xu , You Wu , Ziyu Guan , Wei Zhao

Nowadays, explosive synchronization is a well documented phenomenon occurring in networks when the node frequency and its degree are correlated. This first-order transition, which may coexists with classical synchronization, has been…

Physics and Society · Physics 2023-05-17 Manuel Miranda , Mattia Frasca , Ernesto Estrada