English
Related papers

Related papers: Investigating Alternatives to the Root Mean Square…

200 papers

We provide a simple proof of convergence covering both the Adam and Adagrad adaptive optimization algorithms when applied to smooth (possibly non-convex) objective functions with bounded gradients. We show that in expectation, the squared…

Machine Learning · Statistics 2022-10-18 Alexandre Défossez , Léon Bottou , Francis Bach , Nicolas Usunier

Optimizers like Adam and AdaGrad have been very successful in training large-scale neural networks. Yet, the performance of these methods is heavily dependent on a carefully tuned learning rate schedule. We show that in many large-scale…

Machine Learning · Computer Science 2022-02-02 Ehsan Amid , Rohan Anil , Christopher Fifty , Manfred K. Warmuth

Convex quadratic programs (QPs) constitute a fundamental computational primitive across diverse domains including financial optimization, control systems, and machine learning. The alternating direction method of multipliers (ADMM) has…

Optimization and Control · Mathematics 2025-05-15 Xi Gao , Jinxin Xiong , Linxin Yang , Akang Wang , Weiwei Xu , Jiang Xue

In this work, we study the iteration complexity of gradient methods for minimizing convex quadratic functions regularized by powers of Euclidean norms. We show that, due to the uniform convexity of the objective, gradient methods have…

Optimization and Control · Mathematics 2025-01-28 Daniel Berg Thomsen , Nikita Doikov

L$_2$ regularization and weight decay regularization are equivalent for standard stochastic gradient descent (when rescaled by the learning rate), but as we demonstrate this is \emph{not} the case for adaptive gradient algorithms, such as…

Machine Learning · Computer Science 2019-01-08 Ilya Loshchilov , Frank Hutter

Adaptive gradient methods including Adam, AdaGrad, and their variants have been very successful for training deep learning models, such as neural networks. Meanwhile, given the need for distributed computing, distributed optimization…

Machine Learning · Computer Science 2021-09-08 Xiangyi Chen , Belhal Karimi , Weijie Zhao , Ping Li

Establishing a fast rate of convergence for optimization methods is crucial to their applicability in practice. With the increasing popularity of deep learning over the past decade, stochastic gradient descent and its adaptive variants…

Optimization and Control · Mathematics 2022-01-03 Adityanarayanan Radhakrishnan , Mikhail Belkin , Caroline Uhler

Adam and AdamW are a class of default optimizers for training deep learning models in machine learning. These adaptive algorithms converge faster but generalize worse compared to SGD. In fact, their proved generalization error…

Machine Learning · Computer Science 2026-03-04 Feihu Huang , Guanyi Zhang , Songcan Chen

Stochastic gradient descent (SGD) and adaptive gradient methods, such as Adam and RMSProp, have been widely used in training deep neural networks. We empirically show that while the difference between the standard generalization performance…

Machine Learning · Computer Science 2023-11-30 Avery Ma , Yangchen Pan , Amir-massoud Farahmand

Stochastic methods with coordinate-wise adaptive stepsize (such as RMSprop and Adam) have been widely used in training deep neural networks. Despite their fast convergence, they can generalize worse than stochastic gradient descent. In this…

Machine Learning · Computer Science 2019-05-27 Shuai Zheng , James T. Kwok

As deep learning models exponentially increase in size, optimizers such as Adam encounter significant memory consumption challenges due to the storage of first and second moment data. Current memory-efficient methods like Adafactor and CAME…

Machine Learning · Computer Science 2024-03-25 Pengxiang Zhao , Ping Li , Yingjie Gu , Yi Zheng , Stephan Ludger Kölker , Zhefeng Wang , Xiaoming Yuan

The dynamic behavior of RMSprop and Adam algorithms is studied through a combination of careful numerical experiments and theoretical explanations. Three types of qualitative features are observed in the training loss curve: fast initial…

Machine Learning · Computer Science 2021-10-01 Chao Ma , Lei Wu , Weinan E

Stochastic optimization algorithms using exponential moving averages of the past gradients, such as ADAM, RMSProp and AdaGrad, have been having great successes in many applications, especially in training deep neural networks. ADAM in…

Machine Learning · Computer Science 2026-01-30 Ruiqi Wang , Diego Klabjan

Despite their overwhelming capacity to overfit, deep neural networks trained by specific optimization algorithms tend to generalize well to unseen data. Recently, researchers explained it by investigating the implicit regularization effect…

Machine Learning · Computer Science 2021-12-17 Bohan Wang , Qi Meng , Wei Chen , Tie-Yan Liu

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

Gradient-based first-order adaptive optimization methods such as the Adam optimizer are prevalent in training artificial networks, achieving the state-of-the-art results. This work attempts to answer the question whether it is viable for…

Neural and Evolutionary Computing · Computer Science 2022-12-20 Yukun Yang , Peng Li

The adaptive moment estimation (Adam) optimizer proposed by Kingma & Ba (2014) is presumably the most popular stochastic gradient descent (SGD) optimization method for the training of deep neural networks (DNNs) in artificial intelligence…

Machine Learning · Computer Science 2026-03-20 Steffen Dereich , Thang Do , Arnulf Jentzen

First-order optimization algorithms have been proven prominent in deep learning. In particular, algorithms such as RMSProp and Adam are extremely popular. However, recent works have pointed out the lack of ``long-term memory" in Adam-like…

Machine Learning · Computer Science 2020-12-01 Haiwen Huang , Chang Wang , Bin Dong

Layer normalization (LayerNorm) has been successfully applied to various deep neural networks to help stabilize training and boost model convergence because of its capability in handling re-centering and re-scaling of both inputs and weight…

Machine Learning · Computer Science 2019-10-17 Biao Zhang , Rico Sennrich

Most optimizers including stochastic gradient descent (SGD) and its adaptive gradient derivatives face the same problem where an effective learning rate during the training is vastly different. A learning rate scheduling, mostly tuned by…

Machine Learning · Computer Science 2019-12-30 Konpat Preechakul , Boonserm Kijsirikul