English
Related papers

Related papers: Understanding the Generalization of Stochastic Gra…

200 papers

The Adam optimizer is widely used for transformer optimization in practice, which makes understanding the underlying optimization mechanisms an important problem. However, due to the Adam's complexity, theoretical analysis of how it…

Machine Learning · Computer Science 2025-03-04 Bingrui Li , Wei Huang , Andi Han , Zhanpeng Zhou , Taiji Suzuki , Jun Zhu , Jianfei Chen

Diagonal preconditioners are computationally feasible approximate to second-order optimizers, which have shown significant promise in accelerating training of deep learning models. Two predominant approaches are based on Adam and…

Machine Learning · Computer Science 2025-10-16 Bingbin Liu , Rachit Bansal , Depen Morwani , Nikhil Vyas , David Alvarez-Melis , Sham M. Kakade

Adaptive gradient methods such as RMSProp and Adam use exponential moving estimate of the squared gradient to compute adaptive step sizes, achieving better convergence than SGD in face of noisy objectives. However, Adam can have undesirable…

Machine Learning · Computer Science 2021-07-06 Chen Zhu , Yu Cheng , Zhe Gan , Furong Huang , Jingjing Liu , Tom Goldstein

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

Distributed implementations of mini-batch stochastic gradient descent (SGD) suffer from communication overheads, attributed to the high frequency of gradient updates inherent in small-batch training. Training with large batches can reduce…

Machine Learning · Statistics 2018-06-12 Lingjiao Chen , Hongyi Wang , Jinman Zhao , Dimitris Papailiopoulos , Paraschos Koutris

In this work, we investigate the dynamics of stochastic gradient descent (SGD) when training a single-neuron autoencoder with linear or ReLU activation on orthogonal data. We show that for this non-convex problem, randomly initialized SGD…

Machine Learning · Statistics 2023-08-08 Nikhil Ghosh , Spencer Frei , Wooseok Ha , Bin Yu

Despite the omnipresent use of stochastic gradient descent (SGD) optimization methods in the training of deep neural networks (DNNs), it remains, in basically all practically relevant scenarios, a fundamental open problem to provide a…

Machine Learning · Computer Science 2025-03-04 Thang Do , Arnulf Jentzen , Adrian Riekert

Deep learning optimization relies heavily on the assumption of smooth loss landscapes, a condition systematically violated by modern architectures due to non-smooth components such as ReLU activations and quantization operators. In such…

Machine Learning · Computer Science 2026-05-29 Ruoran Xu , Borong She , Xiaobo Jin , Qiufeng Wang

Weight decay is a simple yet powerful regularization technique that has been very widely used in training of deep neural networks (DNNs). While weight decay has attracted much attention, previous studies fail to discover some overlooked…

Machine Learning · Computer Science 2024-08-19 Zeke Xie , Zhiqiang Xu , Jingzhao Zhang , Issei Sato , Masashi Sugiyama

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 investigate the inherent bias of Stochastic Gradient Descent (SGD) toward learning low-rank weight matrices during the training of deep neural networks. Our results demonstrate that training with mini-batch SGD and weight decay induces a…

Machine Learning · Computer Science 2024-10-22 Tomer Galanti , Zachary S. Siegel , Aparna Gupte , Tomaso Poggio

Current state-of-the-art optimizers are adaptive gradient-based optimization methods such as Adam. Recently, there has been an increasing interest in formulating gradient-based optimizers in a probabilistic framework for better modeling the…

Machine Learning · Computer Science 2025-04-21 Haotian Chen , Anna Kuzina , Babak Esmaeili , Jakub M Tomczak

Recent advances in the theoretical understanding of SGD led to a formula for the optimal batch size minimizing the number of effective data passes, i.e., the number of iterations times the batch size. However, this formula is of no…

Machine Learning · Computer Science 2021-11-22 Motasem Alfarra , Slavomir Hanzely , Alyazeed Albasyoni , Bernard Ghanem , Peter Richtarik

Adam-type optimizers, as a class of adaptive moment estimation methods with the exponential moving average scheme, have been successfully used in many applications of deep learning. Such methods are appealing due to the capability on…

Machine Learning · Computer Science 2020-12-17 Bingxin Zhou , Xuebin Zheng , Junbin Gao

The goal of this paper is to accelerate the training of machine learning models, a critical challenge since the training of large-scale deep neural models can be computationally expensive. Stochastic gradient descent (SGD) and its variants…

Machine Learning · Computer Science 2025-09-22 Yuen Chen , Yian Wang , Hari Sundaram

Stochastic gradient descent (SGD) has been widely studied in the literature from different angles, and is commonly employed for solving many big data machine learning problems. However, the averaging technique, which combines all iterative…

Machine Learning · Computer Science 2020-05-28 Zhishuai Guo , Yan Yan , Tianbao Yang

Training deep neural networks with Stochastic Gradient Descent, or its variants, requires careful choice of both learning rate and batch size. While smaller batch sizes generally converge in fewer training epochs, larger batch sizes offer…

Machine Learning · Computer Science 2018-02-15 Aditya Devarakonda , Maxim Naumov , Michael Garland

Deep learning methods - consisting of a class of deep neural networks (DNNs) trained by a stochastic gradient descent (SGD) optimization method - are nowadays key tools to solve data driven supervised learning problems. Despite the great…

Machine Learning · Computer Science 2025-02-18 Thang Do , Sonja Hannibal , Arnulf Jentzen

It is not clear yet why ADAM-alike adaptive gradient algorithms suffer from worse generalization performance than SGD despite their faster training speed. This work aims to provide understandings on this generalization gap by analyzing…

Machine Learning · Computer Science 2021-11-30 Pan Zhou , Jiashi Feng , Chao Ma , Caiming Xiong , Steven Hoi , Weinan E

SGD (Stochastic Gradient Descent) is a popular algorithm for large scale optimization problems due to its low iterative cost. However, SGD can not achieve linear convergence rate as FGD (Full Gradient Descent) because of the inherent…

Machine Learning · Computer Science 2017-12-05 Aixiang Chen , Bingchuan Chen , Xiaolong Chai , Rui Bian , Hengguang Li