English
Related papers

Related papers: Improving the Adaptive Moment Estimation (ADAM) st…

200 papers

We observe that the traditional use of DP with the Adam optimizer introduces a bias in the second moment estimation, due to the addition of independent noise in the gradient computation. This bias leads to a different scaling for low…

Machine Learning · Computer Science 2023-04-25 Qiaoyue Tang , Mathias Lécuyer

Convergence and convergence rate analyses of adaptive methods, such as Adaptive Moment Estimation (Adam) and its variants, have been widely studied for nonconvex optimization. The analyses are based on assumptions that the expected or…

Machine Learning · Computer Science 2022-06-28 Hideaki Iiduka

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

In this paper, we study the convergence of the Adaptive Moment Estimation (Adam) algorithm under unconstrained non-convex smooth stochastic optimizations. Despite the widespread usage in machine learning areas, its theoretical properties…

Optimization and Control · Mathematics 2023-11-06 Yusu Hong , Junhong Lin

The vast majority of successful deep neural networks are trained using variants of stochastic gradient descent (SGD) algorithms. Recent attempts to improve SGD can be broadly categorized into two approaches: (1) adaptive learning rate…

Machine Learning · Computer Science 2019-12-04 Michael R. Zhang , James Lucas , Geoffrey Hinton , Jimmy Ba

We present a method to formulate algorithm discovery as program search, and apply it to discover optimization algorithms for deep neural network training. We leverage efficient search techniques to explore an infinite and sparse program…

Stochastic regularization of neural networks (e.g. dropout) is a wide-spread technique in deep learning that allows for better generalization. Despite its success, continuous-time models, such as neural ordinary differential equation (ODE),…

Machine Learning · Computer Science 2020-06-29 Viktor Oganesyan , Alexandra Volokhova , Dmitry Vetrov

This paper is concerned with the adaptive numerical treatment of stochastic partial differential equations. Our method of choice is Rothe's method. We use the implicit Euler scheme for the time discretization. Consequently, in each step, an…

We present a hybrid a-priori/a-posteriori goal oriented error estimator for a combination of dynamic iteration-based solution of ordinary differential equations discretized by finite elements. Our novel error estimator combines estimates…

Numerical Analysis · Mathematics 2026-02-13 Erik Weyl , Andreas Bartel , Manuel Schaller

Uncertainty computation in deep learning is essential to design robust and reliable systems. Variational inference (VI) is a promising approach for such computation, but requires more effort to implement and execute compared to…

Machine Learning · Statistics 2018-08-03 Mohammad Emtiyaz Khan , Didrik Nielsen , Voot Tangkaratt , Wu Lin , Yarin Gal , Akash Srivastava

We investigate the role of the optimizer in determining the quality of the model fit for neural networks with a small to medium number of parameters. We study the performance of Adam, an algorithm for first-order gradient-based optimization…

Machine Learning · Computer Science 2022-05-17 John Taylor , Wenyi Wang , Biswajit Bala , Tomasz Bednarz

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

Adam is the go-to optimizer for training modern machine learning models, but it requires additional memory to maintain the moving averages of the gradients and their squares. While various low-memory optimizers have been proposed that…

Machine Learning · Computer Science 2025-03-19 Dayal Singh Kalra , John Kirchenbauer , Maissam Barkeshli , Tom Goldstein

We provide a novel accelerated first-order method that achieves the asymptotically optimal convergence rate for smooth functions in the first-order oracle model. To this day, Nesterov's Accelerated Gradient Descent (AGD) and variations…

Optimization and Control · Mathematics 2018-02-13 Jelena Diakonikolas , Lorenzo Orecchia

A growing number of applications in particle physics and beyond use neural networks as unbinned likelihood ratio estimators applied to real or simulated data. Precision requirements on the inference tasks demand a high-level of stability…

High Energy Physics - Phenomenology · Physics 2025-03-04 G. Bruno De Luca , Benjamin Nachman , Eva Silverstein , Henry Zheng

Distributed stochastic optimization algorithms can simultaneously process large-scale datasets, significantly accelerating model training. However, their effectiveness is often hindered by the sparsity of distributed networks and data…

Machine Learning · Computer Science 2025-02-14 Yuchen Hu , Xi Chen , Weidong Liu , Xiaojun Mao

Adaptive optimizers, most notably Adam, have become the default standard for training large-scale neural networks such as Transformers. These methods maintain running estimates of gradient first and second moments, incurring substantial…

Machine Learning · Computer Science 2026-05-12 Yao Lu , Dengdong Fan , Shixun Zhang , Yonghong Tian

Machine learning pipelines often rely on optimization procedures to make discrete decisions (e.g., sorting, picking closest neighbors, or shortest paths). Although these discrete decisions are easily computed, they break the…

Machine Learning · Computer Science 2020-06-11 Quentin Berthet , Mathieu Blondel , Olivier Teboul , Marco Cuturi , Jean-Philippe Vert , Francis Bach

Adam-type methods, the extension of adaptive gradient methods, have shown great performance in the training of both supervised and unsupervised machine learning models. In particular, Adam-type optimizers have been widely used empirically…

Machine Learning · Computer Science 2021-09-30 Zehao Dou , Yuanzhi Li

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