English
Related papers

Related papers: No More Adam: Learning Rate Scaling at Initializat…

200 papers

Adversarial Training (AT) with Projected Gradient Descent (PGD) is an effective approach for improving the robustness of the deep neural networks. However, PGD AT has been shown to suffer from two main limitations: i) high computational…

Computer Vision and Pattern Recognition · Computer Science 2020-12-29 Ahmadreza Jeddi , Mohammad Javad Shafiee , Alexander Wong

Differentially-Private SGD (DP-SGD) and its adaptive variant DP-Adam are powerful techniques to protect user privacy when using sensitive data to train neural networks. During training, converting model weights and activations into…

Machine Learning · Computer Science 2026-04-17 Yubo Gao , Renbo Tu , Gennady Pekhimenko , Nandita Vijaykumar

Adam is known to perform significantly better than Stochastic Gradient Descent (SGD) in language models, a phenomenon for which a number of explanations have been proposed. In this work, we revisit this "optimizer gap" through a series of…

Machine Learning · Computer Science 2025-06-17 Teodora Srećković , Jonas Geiping , Antonio Orvieto

Theoretically understanding stochastic gradient descent (SGD) in overparameterized models has led to the development of several optimization algorithms that are widely used in practice today. Recent work by~\citet{zou2021benign} provides…

Machine Learning · Computer Science 2025-06-19 Alexandru Meterez , Depen Morwani , Costin-Andrei Oncescu , Jingfeng Wu , Cengiz Pehlevan , Sham Kakade

The training of deep neural networks is inherently a nonconvex optimization problem, yet standard approaches such as stochastic gradient descent (SGD) require simultaneous updates to all parameters, often leading to unstable convergence and…

Machine Learning · Computer Science 2025-08-07 Chengcheng Yan , Jiawei Xu , Zheng Peng , Qingsong Wang

Neural networks are trained by optimizing multi-dimensional sets of fitting parameters on non-convex loss landscapes. Low-loss regions of the landscapes correspond to the parameter sets that perform well on the training data. A key issue in…

Machine Learning · Computer Science 2026-02-26 Jianneng Yu , Alexandre V. Morozov

We propose GradPower, a lightweight gradient-transformation technique for accelerating language model pre-training. Given a gradient vector $g=(g_i)_i$, GradPower first applies the elementwise sign-power transformation: $\varphi_p(g)=({\rm…

Machine Learning · Computer Science 2026-05-21 Jinbo Wang , Mingze Wang , Jiaqi Zhang , Wei Wang , Peng Pei , Xunliang Cai , Weinan E , Lei Wu

Due to their high computational complexity, deep neural networks are still limited to powerful processing units. To promote a reduced model complexity by dint of low-bit fixed-point quantization, we propose a gradient-based optimization…

Machine Learning · Computer Science 2019-07-18 Lukas Enderich , Fabian Timm , Lars Rosenbaum , Wolfram Burgard

The performance of mini-batch stochastic gradient descent (SGD) strongly depends on setting the batch size and learning rate to minimize the empirical loss in training the deep neural network. In this paper, we present theoretical analyses…

Machine Learning · Computer Science 2025-02-17 Hikaru Umeda , Hideaki Iiduka

Despite the vast empirical evidence supporting the efficacy of adaptive optimization methods in deep learning, their theoretical understanding is far from complete. This work introduces novel SDEs for commonly used adaptive optimizers:…

Machine Learning · Computer Science 2025-03-12 Enea Monzio Compagnoni , Tianlin Liu , Rustem Islamov , Frank Norbert Proske , Antonio Orvieto , Aurelien Lucchi

Stochastic gradient descent (SGD) has taken the stage as the primary workhorse for large-scale machine learning. It is often used with its adaptive variants such as AdaGrad, Adam, and AMSGrad. This paper proposes an adaptive stochastic…

Machine Learning · Computer Science 2021-01-01 Tianyi Chen , Ziye Guo , Yuejiao Sun , Wotao Yin

Deep learning networks are typically trained by Stochastic Gradient Descent (SGD) methods that iteratively improve the model parameters by estimating a gradient on a very small fraction of the training data. A major roadblock faced when…

Machine Learning · Computer Science 2020-06-11 Tao Lin , Lingjing Kong , Sebastian U. Stich , Martin Jaggi

Stochastic gradient methods (SGMs) are the predominant approaches to train deep learning models. The adaptive versions (e.g., Adam and AMSGrad) have been extensively used in practice, partly because they achieve faster convergence than the…

Optimization and Control · Mathematics 2022-04-14 Yangyang Xu , Yibo Xu , Yonggui Yan , Colin Sutcher-Shepard , Leopold Grinberg , Jie Chen

The learning rate is an important tuning parameter for stochastic gradient descent (SGD) and can greatly influence its performance. However, appropriate selection of a learning rate schedule across all iterations typically requires a…

Machine Learning · Computer Science 2025-05-29 Nikola Surjanovic , Alexandre Bouchard-Côté , Trevor Campbell

Modern machine learning is trained by stochastic gradient descent (SGD), whose performance critically depends on how the learning rate (LR) is adjusted and decreased over time. Yet existing LR regimes may be intricate, or need to tune one…

Machine Learning · Computer Science 2025-08-20 Zhuang Yang

Stochastic gradient descent~(SGD) and its variants have been the dominating optimization methods in machine learning. Compared to SGD with small-batch training, SGD with large-batch training can better utilize the computational power of…

Machine Learning · Statistics 2024-04-16 Shen-Yi Zhao , Chang-Wei Shi , Yin-Peng Xie , Wu-Jun Li

Training deep neural networks requires intricate initialization and careful selection of learning rates. The emergence of stochastic gradient optimization methods that use adaptive learning rates based on squared past gradients, e.g.,…

Machine Learning · Computer Science 2019-10-29 Jianbang Ding , Xuancheng Ren , Ruixuan Luo , Xu Sun

Iterative procedures for parameter estimation based on stochastic gradient descent allow the estimation to scale to massive data sets. However, in both theory and practice, they suffer from numerical instability. Moreover, they are…

Methodology · Statistics 2016-06-08 Panos Toulis , Dustin Tran , Edoardo M. Airoldi

Sharpness-Aware Minimization (SAM) has recently emerged as a robust technique for improving the accuracy of deep neural networks. However, SAM incurs a high computational cost in practice, requiring up to twice as much computation as…

Machine Learning · Computer Science 2022-10-25 Renkun Ni , Ping-yeh Chiang , Jonas Geiping , Micah Goldblum , Andrew Gordon Wilson , Tom Goldstein

In recent years, large language models (LLMs) have made remarkable progress, with model optimization primarily relying on gradient-based optimizers such as Adam. However, these gradient-based methods impose stringent hardware requirements,…

Artificial Intelligence · Computer Science 2025-10-24 WenTao Liu , Siyu Song , Hao Hao , Aimin Zhou