English
Related papers

Related papers: Batch size invariant Adam

200 papers

We propose the use of U-statistics to reduce variance for gradient estimation in importance-weighted variational inference. The key observation is that, given a base gradient estimator that requires $m > 1$ samples and a total of $n > m$…

Machine Learning · Computer Science 2023-02-28 Javier Burroni , Kenta Takatsu , Justin Domke , Daniel Sheldon

The most straightforward method to accelerate Stochastic Gradient Descent (SGD) computation is to distribute the randomly selected batch of inputs over multiple processors. To keep the distributed processors fully utilized requires…

Machine Learning · Computer Science 2020-01-06 Zhewei Yao , Amir Gholami , Daiyaan Arfeen , Richard Liaw , Joseph Gonzalez , Kurt Keutzer , Michael Mahoney

Increasing the batch size during training -- a ''batch ramp'' -- is a promising strategy to accelerate large language model pretraining. While for SGD, doubling the batch size can be equivalent to halving the learning rate, the optimal…

Machine Learning · Computer Science 2025-10-17 Alexandru Meterez , Depen Morwani , Jingfeng Wu , Costin-Andrei Oncescu , Cengiz Pehlevan , Sham Kakade

Most methods for Bundle Adjustment (BA) in computer vision are either centralized or operate incrementally. This leads to poor scaling and affects the quality of solution as the number of images grows in large scale structure from motion…

Computer Vision and Pattern Recognition · Computer Science 2017-08-29 Karthikeyan Natesan Ramamurthy , Chung-Ching Lin , Aleksandr Aravkin , Sharath Pankanti , Raphael Viguier

Adam is one of the most popular optimization algorithms in deep learning. However, it is known that Adam does not converge in theory unless choosing a hyperparameter, i.e., $\beta_2$, in a problem-dependent manner. There have been many…

When using active learning, smaller batch sizes are typically more efficient from a learning efficiency perspective. However, in practice due to speed and human annotator considerations, the use of larger batch sizes is necessary. While…

Machine Learning · Computer Science 2018-05-18 Garrett Beatty , Ethan Kochis , Michael Bloodgood

For randomized controlled trials to be conclusive, it is important to set the target sample size accurately at the design stage. Comparing two normal populations, the sample size calculation requires specification of the variance other than…

Methodology · Statistics 2026-02-04 Hirotada Maeda , Satoshi Hattori , Tim Friede

In many learning applications, data are collected from multiple sources, each providing a \emph{batch} of samples that by itself is insufficient to learn its input-output relationship. A common approach assumes that the sources fall in one…

Machine Learning · Computer Science 2023-09-06 Ayush Jain , Rajat Sen , Weihao Kong , Abhimanyu Das , Alon Orlitsky

Solving a large-scale system of linear equations is a key step at the heart of many algorithms in machine learning, scientific computing, and beyond. When the problem dimension is large, computational and/or memory constraints make it…

Machine Learning · Computer Science 2017-12-12 Navid Azizan-Ruhi , Farshad Lahouti , Salman Avestimehr , Babak Hassibi

Averaging techniques such as Ruppert--Polyak averaging and exponential movering averaging (EMA) are powerful approaches to accelerate optimization procedures of stochastic gradient descent (SGD) optimization methods such as the popular ADAM…

Optimization and Control · Mathematics 2025-05-29 Arnulf Jentzen , Julian Kranz , Adrian Riekert

In the setting of nonparametric regression, we propose and study a combination of stochastic gradient methods with Nystr\"om subsampling, allowing multiple passes over the data and mini-batches. Generalization error bounds for the studied…

Machine Learning · Statistics 2017-10-24 Junhong Lin , Lorenzo Rosasco

The Adam optimizer is the standard choice in deep learning applications. I propose a simple explanation of Adam's success: it makes each parameter's step size independent of the norms of the other parameters. Based on this principle I…

Machine Learning · Computer Science 2023-07-25 Jacob Jackson

Black-box variational inference (BBVI) scales poorly to high-dimensional problems when it is used to estimate a multivariate Gaussian approximation with a full covariance matrix. In this paper, we extend the batch-and-match (BaM) framework…

Machine Learning · Statistics 2025-04-03 Chirag Modi , Diana Cai , Lawrence K. Saul

Modern deep learning models are over-parameterized, where different optima can result in widely varying generalization performance. The Sharpness-Aware Minimization (SAM) technique modifies the fundamental loss function that steers gradient…

In modern data analysis, random sampling is an efficient and widely-used strategy to overcome the computational difficulties brought by large sample size. In previous studies, researchers conducted random sampling which is according to the…

Machine Learning · Statistics 2018-03-05 Rong Zhu

A crucial component of machine learning algorithms is minimizing loss functions with less computational cost and less oscillations. While adaptive learning rate-based optimizers have been widely used for real-world tasks, they do not…

Machine Learning · Computer Science 2026-05-29 Sakshi Kumari , Shyam Kumar M , Sushmitha P

By coordinating terminal smart devices or microprocessors to engage in cooperative computation to achieve systemlevel targets, distributed optimization is incrementally favored by both engineering and computer science. The well-known…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-08-24 Yu Yang , Xiaohong Guan , Qing-Shan Jia , Liang Yu , Bolun Xu , Costas J. Spanos

We address the issue of performing testing inference in generalized linear models when the sample size is small. This class of models provides a straightforward way of modeling normal and non-normal data and has been widely used in several…

Methodology · Statistics 2013-08-16 Tiago M. Vargas , Silvia L. P. Ferrari , Artur J. Lemonte

The alternating direction method of multipliers (ADMM) has been popular for solving many signal processing problems, convex or nonconvex. In this paper, we study an asynchronous implementation of the ADMM for solving a nonconvex nonsmooth…

Information Theory · Computer Science 2014-12-19 Mingyi Hong

We introduce Gradient Agreement Filtering (GAF) to improve on gradient averaging in distributed deep learning optimization. Traditional distributed data-parallel stochastic gradient descent involves averaging gradients of microbatches to…

Machine Learning · Computer Science 2024-12-31 Francois Chaubard , Duncan Eddy , Mykel J. Kochenderfer