English
Related papers

Related papers: Cosine-Gated Adam-Decay: Drop-In Staleness-Aware O…

200 papers

Stochastic optimizers are central to deep learning, yet widely used methods such as Adam and Adan can degrade in non-stationary or noisy environments, partly due to their reliance on momentum-based magnitude estimates. We introduce Ano, a…

Machine Learning · Computer Science 2025-11-11 Adrien Kegreisz

Following the introduction of Adam, several novel adaptive optimizers for deep learning have been proposed. These optimizers typically excel in some tasks but may not outperform Adam uniformly across all tasks. In this work, we introduce…

Machine Learning · Computer Science 2024-06-18 Kaan Ozkara , Can Karakus , Parameswaran Raman , Mingyi Hong , Shoham Sabach , Branislav Kveton , Volkan Cevher

Stochastic Gradient Descent (SGD) with adaptive steps is widely used to train deep neural networks and generative models. Most theoretical results assume that it is possible to obtain unbiased gradient estimators, which is not the case in…

Machine Learning · Statistics 2025-03-17 Sobihan Surendran , Antoine Godichon-Baggioni , Adeline Fermanian , Sylvain Le Corff

Block coordinate descent is a powerful algorithmic template suitable for big data optimization. This template admits a lot of variants including block gradient descent (BGD), which performs gradient descent on a selected block of variables,…

Optimization and Control · Mathematics 2024-05-28 Liangzu Peng , Wotao Yin

This paper introduces EXAdam ($\textbf{EX}$tended $\textbf{Adam}$), a novel optimization algorithm that builds upon the widely-used Adam optimizer. EXAdam incorporates two key enhancements: (1) new debiasing terms for improved moment…

Machine Learning · Computer Science 2025-05-19 Ahmed M. Adly

In the context of stochastic gradient descent(SGD) and adaptive moment estimation (Adam),researchers have recently proposed optimization techniques that transition from Adam to SGD with the goal of improving both convergence and…

Machine Learning · Computer Science 2020-07-01 Jiaxuan Wang , Jenna Wiens

Differentially Private Stochastic Gradient Descent (DP-SGD) is a widely adopted technique for privacy-preserving deep learning. A critical challenge in DP-SGD is selecting the optimal clipping threshold C, which involves balancing the…

Machine Learning · Computer Science 2025-04-02 Chengkun Wei , Weixian Li , Chen Gong , Wenzhi Chen

The success of deep learning can be attributed to various factors such as increase in computational power, large datasets, deep convolutional neural networks, optimizers etc. Particularly, the choice of optimizer affects the generalization,…

Machine Learning · Computer Science 2021-09-10 Anirudh Maiya , Inumella Sricharan , Anshuman Pandey , Srinivas K. S

We consider the setting where a master wants to run a distributed stochastic gradient descent (SGD) algorithm on $n$ workers, each having a subset of the data. Distributed SGD may suffer from the effect of stragglers, i.e., slow or…

Machine Learning · Computer Science 2022-08-08 Serge Kas Hanna , Rawad Bitar , Parimal Parag , Venkat Dasari , Salim El Rouayheb

Distributed Stochastic Gradient Descent (SGD) when run in a synchronous manner, suffers from delays in runtime as it waits for the slowest workers (stragglers). Asynchronous methods can alleviate stragglers, but cause gradient staleness…

Machine Learning · Statistics 2020-03-25 Sanghamitra Dutta , Jianyu Wang , Gauri Joshi

In this paper, we revisit stochastic gradient descent (SGD) with AdaGrad-type preconditioning. Our contributions are twofold. First, we develop a unified convergence analysis of SGD with adaptive preconditioning under anisotropic or matrix…

Machine Learning · Computer Science 2025-07-01 Dmitry Kovalev

Convolutional neural networks (CNNs) have shown very appealing performance for many computer vision applications. The training of CNNs is generally performed using stochastic gradient descent (SGD) based optimization techniques. The…

Computer Vision and Pattern Recognition · Computer Science 2022-07-20 Sumanth Sadu , Shiv Ram Dubey , SR Sreeja

We propose a stochastic optimization method for minimizing loss functions, expressed as an expected value, that adaptively controls the batch size used in the computation of gradient approximations and the step size used to move along such…

Machine Learning · Computer Science 2020-03-04 Achraf Bahamou , Donald Goldfarb

Asynchronous optimization algorithms often require delay bounds to prove their convergence, though these bounds can be difficult to obtain in practice. Existing algorithms that do not require delay bounds often converge slowly. Therefore,…

Optimization and Control · Mathematics 2025-08-12 Ellie Pond , Yichen Zhao , Matthew Hale

With the increase in the amount of data and the expansion of model scale, distributed parallel training becomes an important and successful technique to address the optimization challenges. Nevertheless, although distributed stochastic…

Machine Learning · Computer Science 2019-09-23 Shuheng Shen , Linli Xu , Jingchang Liu , Xianfeng Liang , Yifei Cheng

Adaptive gradient algorithms perform gradient-based updates using the history of gradients and are ubiquitous in training deep neural networks. While adaptive gradient methods theory is well understood for minimization problems, the…

Optimization and Control · Mathematics 2020-12-29 Mingrui Liu , Youssef Mroueh , Jerret Ross , Wei Zhang , Xiaodong Cui , Payel Das , Tianbao Yang

Asynchronous stochastic gradient descent (ASGD) is a popular parallel optimization algorithm in machine learning. Most theoretical analysis on ASGD take a discrete view and prove upper bounds for their convergence rates. However, the…

Machine Learning · Statistics 2018-05-09 Li He , Qi Meng , Wei Chen , Zhi-Ming Ma , Tie-Yan Liu

Adaptive gradient methods have become popular in optimizing deep neural networks; recent examples include AdaGrad and Adam. Although Adam usually converges faster, variations of Adam, for instance, the AdaBelief algorithm, have been…

Machine Learning · Computer Science 2024-10-29 Kushal Chakrabarti , Nikhil Chopra

The gentlest ascent dynamics (GAD) (Nonlinearity, vol. 24, no. 6, p1831, 2011) is a continuous time dynamics coupling both the position and the direction variables to efficiently locate the saddle point with a given index. These saddle…

Dynamical Systems · Mathematics 2021-12-08 Shuting Gu , Xiang Zhou

Traditional analyses in non-convex optimization typically rely on the smoothness assumption, namely requiring the gradients to be Lipschitz. However, recent evidence shows that this smoothness condition does not capture the properties of…

Machine Learning · Computer Science 2022-08-25 Michael Crawshaw , Mingrui Liu , Francesco Orabona , Wei Zhang , Zhenxun Zhuang