English
Related papers

Related papers: Leveraging Continuous Time to Understand Momentum …

200 papers

We present a manifestly covariant formulation of the gradient descent method, ensuring consistency across arbitrary coordinate systems and general curved trainable spaces. The optimization dynamics is defined using a covariant force vector…

Machine Learning · Computer Science 2025-04-15 Dmitry Guskov , Vitaly Vanchurin

Stochastic gradient descent with momentum (SGDM) methods have become fundamental optimization tools in machine learning, combining the computational efficiency of stochastic gradients with the acceleration benefits of momentum. Despite…

Optimization and Control · Mathematics 2026-03-02 Zimeng Wang , Alp Yurtsever

Any gradient descent optimization requires to choose a learning rate. With deeper and deeper models, tuning that learning rate can easily become tedious and does not necessarily lead to an ideal convergence. We propose a variation of the…

Machine Learning · Statistics 2018-04-10 Mathieu Ravaut , Satya Gorti

This paper presents a novel coordinate descent algorithm leveraging a combination of one-directional line search and gradient information for parameter updates for a squared error loss function. Each parameter undergoes updates determined…

Machine Learning · Computer Science 2024-08-05 Yen-Che Hsiao , Abhishek Dutta

Understanding the behavior of stochastic gradient methods is a central problem in modern machine learning. Recent work has highlighted diagonal linear networks as a simplified yet expressive setting for analyzing the optimization and…

Optimization and Control · Mathematics 2026-05-19 Begoña García Malaxechebarría , Courtney Paquette , Maryam Fazel , Dmitriy Drusvyatskiy

We propose a new discrete-time online parameter estimation algorithm that combines two different aspects, one that adds momentum, and another that includes a time-varying learning rate. It is well known that recursive least squares based…

Optimization and Control · Mathematics 2023-03-21 Yingnan Cui , Anuradha M. Annaswamy

We study a new two-time-scale stochastic gradient method for solving optimization problems, where the gradients are computed with the aid of an auxiliary variable under samples generated by time-varying MDPs controlled by the underlying…

Optimization and Control · Mathematics 2024-08-27 Sihan Zeng , Thinh T. Doan , Justin Romberg

Backpropagation with gradient descent is a common optimization strategy employed by most neural network architectures in machine learning. However, finding optimal hyperparameters to guide training has proven challenging. While it is widely…

Machine Learning · Computer Science 2026-05-20 Vy Bui , Hang Yu , Karthik Kantipudi , Ziv Yaniv , Stefan Jaeger

We study the training dynamics of shallow neural networks, in a two-timescale regime in which the stepsizes for the inner layer are much smaller than those for the outer layer. In this regime, we prove convergence of the gradient flow to a…

Optimization and Control · Mathematics 2023-10-26 Pierre Marion , Raphaël Berthier

We study the generalization performance of gradient methods in the fundamental stochastic convex optimization setting, focusing on its dimension dependence. First, for full-batch gradient descent (GD) we give a construction of a learning…

Machine Learning · Computer Science 2024-01-23 Matan Schliserman , Uri Sherman , Tomer Koren

A theoretical, and potentially also practical, problem with stochastic gradient descent is that trajectories may escape to infinity. In this note, we investigate uniform boundedness properties of iterates and function values along the…

Machine Learning · Computer Science 2022-06-23 Xiaoyu Wang , Mikael Johansson

We study the gradient descent (GD) dynamics of a depth-2 linear neural network with a single input and output. We show that GD converges at an explicit linear rate to a global minimum of the training loss, even with a large stepsize --…

Machine Learning · Computer Science 2025-01-22 Pierfrancesco Beneventano , Blake Woodworth

We conjecture that the inherent difference in generalisation between adaptive and non-adaptive gradient methods in deep learning stems from the increased estimation noise in the flattest directions of the true loss surface. We demonstrate…

Machine Learning · Statistics 2022-03-17 Diego Granziol , Nicholas Baskerville

We demonstrate the possibility of what we call sparse learning: accelerated training of deep neural networks that maintain sparse weights throughout training while achieving dense performance levels. We accomplish this by developing sparse…

Machine Learning · Computer Science 2019-08-27 Tim Dettmers , Luke Zettlemoyer

Although gradient descent with Polyak's momentum is widely used in modern machine and deep learning, a concrete understanding of its effects on the training trajectory remains elusive. In this work, we empirically show that for linear…

Machine Learning · Computer Science 2024-05-30 Prin Phunyaphibarn , Junghyun Lee , Bohan Wang , Huishuai Zhang , Chulhee Yun

Stochastic gradient descent with momentum (SGDM) has been widely used in many machine learning and statistical applications. Despite the observed empirical benefits of SGDM over traditional SGD, the theoretical understanding of the role of…

Machine Learning · Computer Science 2024-02-02 Kejie Tang , Weidong Liu , Yichen Zhang , Xi Chen

We introduce a machine-learning framework to learn the hyperparameter sequence of first-order methods (e.g., the step sizes in gradient descent) to quickly solve parametric convex optimization problems. Our computational architecture…

Optimization and Control · Mathematics 2024-12-23 Rajiv Sambharya , Bartolomeo Stellato

Gradient descent finds a global minimum in training deep neural networks despite the objective function being non-convex. The current paper proves gradient descent achieves zero training loss in polynomial time for a deep over-parameterized…

Machine Learning · Computer Science 2019-05-30 Simon S. Du , Jason D. Lee , Haochuan Li , Liwei Wang , Xiyu Zhai

The problem of finding a solution to the linear system $Ax = b$ with certain minimization properties arises in numerous scientific and engineering areas. In the era of big data, the stochastic optimization algorithms become increasingly…

Numerical Analysis · Mathematics 2026-01-05 Yun Zeng , Deren Han , Yansheng Su , Jiaxin Xie

We theoretically characterize gradient descent dynamics in deep linear networks trained at large width from random initialization and on large quantities of random data. Our theory captures the ``wider is better" effect of…

Machine Learning · Computer Science 2025-06-17 Blake Bordelon , Cengiz Pehlevan