English
Related papers

Related papers: GradientStabilizer:Fix the Norm, Not the Gradient

200 papers

Stochastic optimization plays a crucial role in the advancement of deep learning technologies. Over the decades, significant effort has been dedicated to improving the training efficiency and robustness of deep neural networks, via various…

Machine Learning · Computer Science 2024-08-21 Huixiu Jiang , Ling Yang , Yu Bao , Rutong Si , Sikun Yang

Training deep belief networks (DBNs) requires optimizing a non-convex function with an extremely large number of parameters. Naturally, existing gradient descent (GD) based methods are prone to arbitrarily poor local minima. In this paper,…

Machine Learning · Computer Science 2015-03-09 Prateek Jain , Vivek Kulkarni , Abhradeep Thakurta , Oliver Williams

Gradient descent prevails in artificial neural network training, but seems inept for spiking neural networks as small parameter changes can cause sudden, disruptive (dis-)appearances of spikes. Here, we demonstrate exact gradient descent…

Neurons and Cognition · Quantitative Biology 2025-01-29 Christian Klos , Raoul-Martin Memmesheimer

This paper presents a gradient-informed fine-tuning method for large language models under few-shot conditions. The goal is to enhance task adaptability and training stability when data is limited. The method builds on a base loss function…

Computation and Language · Computer Science 2025-06-03 Hongye Zheng , Yichen Wang , Ray Pan , Guiran Liu , Binrong Zhu , Hanlu Zhang

Gradient clipping is commonly used in training deep neural networks partly due to its practicability in relieving the exploding gradient problem. Recently, \citet{zhang2019gradient} show that clipped (stochastic) Gradient Descent (GD)…

Machine Learning · Computer Science 2020-10-30 Bohang Zhang , Jikai Jin , Cong Fang , Liwei Wang

Deep neural networks have been shown to achieve state-of-the-art performance in several machine learning tasks. Stochastic Gradient Descent (SGD) is the preferred optimization algorithm for training these networks and asynchronous SGD…

Machine Learning · Computer Science 2016-04-06 Wei Zhang , Suyog Gupta , Xiangru Lian , Ji Liu

Gradient descent (GD) based optimization methods are these days the standard tools to train deep neural networks in artificial intelligence systems. In optimization procedures in deep learning the employed optimizer is often not the…

Optimization and Control · Mathematics 2025-09-24 Steffen Dereich , Robin Graeber , Arnulf Jentzen , Adrian Riekert

We introduce a new technique for gradient normalization during neural network training. The gradients are rescaled during the backward pass using normalization layers introduced at certain points within the network architecture. These…

Machine Learning · Computer Science 2021-06-18 Alejandro Cabana , Luis F. Lago-Fernández

Gradient clipping is a standard safeguard for training neural networks under noisy, heavy-tailed stochastic gradients; yet, most clipping rules treat all parameters as vectors and ignore the matrix structure of modern architectures. We show…

Machine Learning · Computer Science 2026-05-13 Alexander Yukhimchuk , Mladen Kolar , Martin Takáč , Sayantan Choudhury

Training modern neural networks is increasingly fragile, with rare but severe destabilizing updates often causing irreversible divergence or silent performance degradation. Existing optimization methods primarily rely on preventive…

Machine Learning · Computer Science 2026-01-27 Barak Or

Most popular optimizers for deep learning can be broadly categorized as adaptive methods (e.g. Adam) and accelerated schemes (e.g. stochastic gradient descent (SGD) with momentum). For many models such as convolutional neural networks…

Machine Learning · Computer Science 2020-12-22 Juntang Zhuang , Tommy Tang , Yifan Ding , Sekhar Tatikonda , Nicha Dvornek , Xenophon Papademetris , James S. Duncan

This work addresses the instability in asynchronous data parallel optimization. It does so by introducing a novel distributed optimizer which is able to efficiently optimize a centralized model under communication constraints. The optimizer…

Machine Learning · Statistics 2017-10-09 Joeri Hermans , Gerasimos Spanakis , Rico Möckel

Fine-tuning over large pretrained language models (PLMs) has established many state-of-the-art results. Despite its superior performance, such fine-tuning can be unstable, resulting in significant variance in performance and potential risks…

Computation and Language · Computer Science 2022-10-20 Chenghao Yang , Xuezhe Ma

We examine the stability of loss-minimizing training processes that are used for deep neural networks (DNN) and other classifiers. While a classifier is optimized during training through a so-called loss function, the performance of…

Analysis of PDEs · Mathematics 2020-10-05 Leonid Berlyand , Pierre-Emmanuel Jabin , C. Alex Safsten

Privacy-preserving training on sensitive data commonly relies on differentially private stochastic optimization with gradient clipping and Gaussian noise. The clipping threshold is a critical control knob: if set too small, systematic…

Machine Learning · Computer Science 2026-02-12 Mohammad Partohaghighi , Roummel Marcia , Bruce J. West , YangQuan Chen

Deep neural network training involves both forward propagation (from features through logits to loss) and backward propagation (from loss through gradients to parameter updates). While perturbations along the forward chain, including…

Machine Learning · Computer Science 2026-05-29 Hua Li

We introduce Velocity-Regularized Adam (VRAdam), a physics-inspired optimizer for training deep neural networks that draws on ideas from quartic terms for kinetic energy with its stabilizing effects on various system dynamics. Previous…

Machine Learning · Computer Science 2026-05-13 Pranav Vaidhyanathan , Lucas Schorling , Natalia Ares , Michael A. Osborne

Training very deep neural networks requires controlling the propagation of magnitudes across depth. Without such control, activations and gradients may vanish, explode, or enter unstable regimes that make optimization fail. Modern…

In deep learning, optimization plays a vital role. By focusing on image classification, this work investigates the pros and cons of the widely used optimizers, and proposes a new optimizer: Perturbated Unit Gradient Descent (PUGD) algorithm…

Machine Learning · Computer Science 2022-11-10 Ching-Hsun. Tseng , Liu-Hsueh. Cheng , Shin-Jye. Lee , Xiaojun Zeng

The impact of gradient noise on training deep models is widely acknowledged but not well understood. In this context, we study the distribution of gradients during training. We introduce a method, Gradient Clustering, to minimize the…

Machine Learning · Computer Science 2020-07-10 Fartash Faghri , David Duvenaud , David J. Fleet , Jimmy Ba