English
Related papers

Related papers: Towards Theoretically Understanding Why SGD Genera…

200 papers

Adam is the de facto optimization algorithm for several deep learning applications, but an understanding of its implicit bias and how it differs from other algorithms, particularly standard first-order methods such as (stochastic) gradient…

Machine Learning · Computer Science 2025-10-27 Bhavya Vasudeva , Jung Whan Lee , Vatsal Sharan , Mahdi Soltanolkotabi

Adaptive optimization methods, which perform local optimization with a metric constructed from the history of iterates, are becoming increasingly popular for training deep neural networks. Examples include AdaGrad, RMSProp, and Adam. We…

Machine Learning · Statistics 2018-05-23 Ashia C. Wilson , Rebecca Roelofs , Mitchell Stern , Nathan Srebro , Benjamin Recht

The stochastic gradient descent (SGD) method and its variants are algorithms of choice for many Deep Learning tasks. These methods operate in a small-batch regime wherein a fraction of the training data, say $32$-$512$ data points, is…

Machine Learning · Computer Science 2017-02-13 Nitish Shirish Keskar , Dheevatsa Mudigere , Jorge Nocedal , Mikhail Smelyanskiy , Ping Tak Peter Tang

Deep learning algorithms - typically consisting of a class of deep neural networks trained by a stochastic gradient descent (SGD) optimization method - are nowadays the key ingredients in many artificial intelligence (AI) systems and have…

Machine Learning · Computer Science 2024-07-12 Steffen Dereich , Robin Graeber , Arnulf Jentzen

Adaptive gradient methods, such as AdaGrad, are among the most successful optimization algorithms for neural network training. While these methods are known to achieve better dimensional dependence than stochastic gradient descent (SGD) for…

Optimization and Control · Mathematics 2025-06-09 Ruichen Jiang , Devyani Maladkar , Aryan Mokhtari

Stochastic gradient descent (SGD) algorithm and its variations have been effectively used to optimize neural network models. However, with the rapid growth of big data and deep learning, SGD is no longer the most suitable choice due to its…

Machine Learning · Computer Science 2024-02-13 Anuraganand Sharma

In this work, we reveal a strong implicit bias of stochastic gradient descent (SGD) that drives overly expressive networks to much simpler subnetworks, thereby dramatically reducing the number of independent parameters, and improving…

Machine Learning · Computer Science 2024-05-30 Feng Chen , Daniel Kunin , Atsushi Yamamura , Surya Ganguli

Stochastic Gradient Descent (SGD) is a cornerstone of large-scale optimization, yet its theoretical behavior under heavy-tailed noise -- common in modern machine learning and reinforcement learning -- remains poorly understood. In this…

Optimization and Control · Mathematics 2025-08-08 Ilyas Fatkhullin , Florian Hübler , Guanghui Lan

Stochastic Gradient Descent (SGD) is the workhorse algorithm of deep learning technology. At each step of the training phase, a mini batch of samples is drawn from the training dataset and the weights of the neural network are adjusted…

Disordered Systems and Neural Networks · Physics 2022-09-07 Francesca Mignacco , Pierfrancesco Urbani

The noise in stochastic gradient descent (SGD), caused by minibatch sampling, is poorly understood despite its practical importance in deep learning. This work presents the first systematic study of the SGD noise and fluctuations close to a…

Machine Learning · Computer Science 2022-03-09 Liu Ziyin , Kangqiao Liu , Takashi Mori , Masahito Ueda

We show that stochastic gradient descent (SGD) escapes from sharp minima exponentially fast even before SGD reaches stationary distribution. SGD has been a de-facto standard training algorithm for various machine learning tasks. However,…

Machine Learning · Computer Science 2022-03-22 Hikaru Ibayashi , Masaaki Imaizumi

Stochastic gradient descent with momentum (SGDm) is one of the most popular optimization algorithms in deep learning. While there is a rich theory of SGDm for convex problems, the theory is considerably less developed in the context of deep…

Machine Learning · Statistics 2020-11-05 Umut Şimşekli , Lingjiong Zhu , Yee Whye Teh , Mert Gürbüzbalaban

We introduce a general framework for nonlinear stochastic gradient descent (SGD) for the scenarios when gradient noise exhibits heavy tails. The proposed framework subsumes several popular nonlinearity choices, like clipped, normalized,…

Optimization and Control · Mathematics 2022-04-07 Dusan Jakovetic , Dragana Bajovic , Anit Kumar Sahu , Soummya Kar , Nemanja Milosevic , Dusan Stamenkovic

The ADAM optimizer is exceedingly popular in the deep learning community. Often it works very well, sometimes it doesn't. Why? We interpret ADAM as a combination of two aspects: for each weight, the update direction is determined by the…

Machine Learning · Computer Science 2020-12-15 Lukas Balles , Philipp Hennig

There is an increasing realization that algorithmic inductive biases are central in preventing overfitting; empirically, we often see a benign overfitting phenomenon in overparameterized settings for natural learning algorithms, such as…

Machine Learning · Computer Science 2021-10-14 Difan Zou , Jingfeng Wu , Vladimir Braverman , Quanquan Gu , Sham M. Kakade

Adam is a popular and widely used adaptive gradient method in deep learning, which has also received tremendous focus in theoretical research. However, most existing theoretical work primarily analyzes its full-batch version, which differs…

Machine Learning · Computer Science 2025-10-14 Xuan Tang , Han Zhang , Yuan Cao , Difan Zou

We give a new separation result between the generalization performance of stochastic gradient descent (SGD) and of full-batch gradient descent (GD) in the fundamental stochastic convex optimization model. While for SGD it is well-known that…

Machine Learning · Computer Science 2021-07-01 Idan Amir , Tomer Koren , Roi Livni

Stochastic gradient descent (SGD) performed in an asynchronous manner plays a crucial role in training large-scale machine learning models. However, the generalization performance of asynchronous delayed SGD, which is an essential metric…

Machine Learning · Computer Science 2025-05-27 Xiaoge Deng , Li Shen , Shengwei Li , Tao Sun , Dongsheng Li , Dacheng Tao

The phenomenon that stochastic gradient descent (SGD) favors flat minima has played a critical role in understanding the implicit regularization of SGD. In this paper, we provide an explanation of this striking phenomenon by relating the…

Machine Learning · Statistics 2022-10-18 Lei Wu , Mingze Wang , Weijie Su

Stochastic gradient descent (SGD) and its variants are mainstream methods to train deep neural networks. Since neural networks are non-convex, more and more works study the dynamic behavior of SGD and the impact to its generalization,…

Machine Learning · Computer Science 2020-10-13 Qi Meng , Shiqi Gong , Wei Chen , Zhi-Ming Ma , Tie-Yan Liu