English
Related papers

Related papers: AlphaGrad: Non-Linear Gradient Normalization Optim…

200 papers

The performance of an optimizer on large-scale deep learning models depends critically on fine-tuning the learning rate, often requiring an extensive grid search over base learning rates, schedules, and other hyperparameters. In this paper,…

Machine Learning · Computer Science 2025-06-11 Ruichen Jiang , Ali Kavis , Aryan Mokhtari

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…

We introduce two complementary techniques for efficient optimization that reduce memory requirements while accelerating training of large-scale neural networks. The first technique, Subset-Norm step size, generalizes AdaGrad-Norm and…

Machine Learning · Computer Science 2025-05-27 Thien Hang Nguyen , Huy Le Nguyen

Adam is a widely used stochastic optimization method for deep learning applications. While practitioners prefer Adam because it requires less parameter tuning, its use is problematic from a theoretical point of view since it may not…

Machine Learning · Computer Science 2020-11-25 Mingrui Liu , Wei Zhang , Francesco Orabona , Tianbao Yang

Reinforcement learning (RL), particularly RL from verifiable reward (RLVR), has become a crucial phase of training large language models (LLMs) and a key focus of current scaling efforts. However, optimization practices in RL largely follow…

Machine Learning · Computer Science 2026-02-25 Sagnik Mukherjee , Lifan Yuan , Pavan Jayasinha , Dilek Hakkani-Tür , Hao Peng

We consider the problem of estimating the learning rate in adaptive methods, such as AdaGrad and Adam. We propose Prodigy, an algorithm that provably estimates the distance to the solution $D$, which is needed to set the learning rate…

Machine Learning · Computer Science 2024-03-21 Konstantin Mishchenko , Aaron Defazio

Minimax optimization recently is widely applied in many machine learning tasks such as generative adversarial networks, robust learning and reinforcement learning. In the paper, we study a class of nonconvex-nonconcave minimax optimization…

Optimization and Control · Mathematics 2025-04-23 Feihu Huang , Chunyu Xuan , Xinrui Wang , Siqi Zhang , Songcan Chen

Adam is a commonly used stochastic optimization algorithm in machine learning. However, its convergence is still not fully understood, especially in the non-convex setting. This paper focuses on exploring hyperparameter settings for the…

Optimization and Control · Mathematics 2025-02-12 Meixuan He , Yuqing Liang , Jinlan Liu , Dongpo Xu

Stochastic gradient descent (SGD) is the main approach for training deep networks: it moves towards the optimum of the cost function by iteratively updating the parameters of a model in the direction of the gradient of the loss evaluated on…

Machine Learning · Computer Science 2021-03-30 Loris Nanni , Gianluca Maguolo , Alessandra Lumini

Adaptive optimizers with decoupled weight decay, such as AdamW, are the de facto standard for pre-training large transformer-based generative models. Yet the quadratic nature of the $\ell_2$ penalty embedded in weight decay drives all…

Machine Learning · Computer Science 2025-11-19 Fu-Ming Guo , Yingfang Fan

Standard mixed-precision training of neural networks requires many bytes of accelerator memory for each model parameter. These bytes reflect not just the parameter itself, but also its gradient and one or more optimizer state variables.…

Machine Learning · Computer Science 2026-03-13 Jose Javier Gonzalez Ortiz , Abhay Gupta , Christopher Rinard , Davis Blalock

Adaptive gradient methods, especially Adam-type methods (such as Adam, AMSGrad, and AdaBound), have been proposed to speed up the training process with an element-wise scaling term on learning rates. However, they often generalize poorly…

Machine Learning · Computer Science 2021-07-20 Zhou Shao , Tong Lin

Adaptive gradient methods are typically used for training over-parameterized models. To better understand their behaviour, we study a simplistic setting -- smooth, convex losses with models over-parameterized enough to interpolate the data.…

Machine Learning · Computer Science 2021-02-22 Sharan Vaswani , Issam Laradji , Frederik Kunstner , Si Yi Meng , Mark Schmidt , Simon Lacoste-Julien

The vast majority of modern deep learning models are trained with momentum-based first-order optimizers. The momentum term governs the optimizer's memory by determining how much each past gradient contributes to the current convergence…

Machine Learning · Computer Science 2026-05-12 Kristi Topollai , Anna Choromanska

Adam-type algorithms have become a preferred choice for optimisation in the deep learning setting, however, despite success, their convergence is still not well understood. To this end, we introduce a unified framework for Adam-type…

Machine Learning · Computer Science 2024-09-24 Yiming Jiang , Jinlan Liu , Dongpo Xu , Danilo P. Mandic

We introduce Gravity, another algorithm for gradient-based optimization. In this paper, we explain how our novel idea change parameters to reduce the deep learning model's loss. It has three intuitive hyper-parameters that the best values…

Machine Learning · Computer Science 2021-01-25 Dariush Bahrami , Sadegh Pouriyan Zadeh

Several recently proposed stochastic optimization methods that have been successfully used in training deep networks such as RMSProp, Adam, Adadelta, Nadam are based on using gradient updates scaled by square roots of exponential moving…

Machine Learning · Computer Science 2019-04-22 Sashank J. Reddi , Satyen Kale , Sanjiv Kumar

Learning rate adaptation is a popular topic in machine learning. Gradient Descent trains neural nerwork with a fixed learning rate. Learning rate adaptation is proposed to accelerate the training process through adjusting the step size in…

Machine Learning · Computer Science 2022-10-20 Bozhou Chen , Hongzhi Wang , Chenmin Ba

We propose ActiveLR, an optimization meta algorithm that localizes the learning rate, $\alpha$, and adapts them at each epoch according to whether the gradient at each epoch changes sign or not. This sign-conscious algorithm is aware of…

Machine Learning · Computer Science 2023-01-25 Davood Wadi , Marc Fredette , Sylvain Senecal

The adaptive moment estimation algorithm Adam (Kingma and Ba) is a popular optimizer in the training of deep neural networks. However, Reddi et al. have recently shown that the convergence proof of Adam is problematic and proposed a variant…

Machine Learning · Computer Science 2019-11-01 Tran Thi Phuong , Le Trieu Phong