English
Related papers

Related papers: Last-Iterate Convergence of Saddle-Point Optimizer…

200 papers

The least absolute shrinkage and selection operator (Lasso) is widely recognized across various fields of mathematics and engineering. Its variant, the generalized Lasso, finds extensive application in the fields of statistics, machine…

Optimization and Control · Mathematics 2024-03-22 Bowen Li , Bin Shi

Gradient descent (GD) and stochastic gradient descent (SGD) are the workhorses of large-scale machine learning. While classical theory focused on analyzing the performance of these methods in convex optimization problems, the most notable…

Machine Learning · Computer Science 2019-09-05 Chi Jin , Praneeth Netrapalli , Rong Ge , Sham M. Kakade , Michael I. Jordan

Balancing convergence speed, generalization capability, and computational efficiency remains a core challenge in deep learning optimization. First-order gradient descent methods, epitomized by stochastic gradient descent (SGD) and Adam,…

Memory-efficient optimization methods have recently gained increasing attention for scaling full-parameter training of large language models under the GPU-memory bottleneck. Existing approaches either lack clear convergence guarantees, or…

Machine Learning · Computer Science 2026-03-11 Hui Yang , Tao Ren , Jinyang Jiang , Wan Tian , Yijie Peng

The rapid advancements in high-dimensional statistics and machine learning have increased the use of first-order methods. Many of these methods can be regarded as instances of the proximal point algorithm. Given the importance of the…

Optimization and Control · Mathematics 2024-11-05 Ya-xiang Yuan , Yi Zhang

Discrete gradient methods are geometric integration techniques that can preserve the dissipative structure of gradient flows. Due to the monotonic decay of the function values, they are well suited for general convex and nonconvex…

Optimization and Control · Mathematics 2024-07-17 Matthias J. Ehrhardt , Erlend S. Riis , Torbjørn Ringholm , Carola-Bibiane Schönlieb

In centralized settings, it is well known that stochastic gradient descent (SGD) avoids saddle points and converges to local minima in nonconvex problems. However, similar guarantees are lacking for distributed first-order algorithms. The…

Optimization and Control · Mathematics 2022-03-07 Brian Swenson , Ryan Murray , H. Vincent Poor , Soummya Kar

Stochastic gradient descent (SGD) is a simple and popular method to solve stochastic optimization problems which arise in machine learning. For strongly convex problems, its convergence rate was known to be O(\log(T)/T), by running SGD for…

Machine Learning · Computer Science 2015-03-19 Alexander Rakhlin , Ohad Shamir , Karthik Sridharan

In this paper, we consider multi-agent learning via online gradient descent in a class of games called $\lambda$-cocoercive games, a fairly broad class of games that admits many Nash equilibria and that properly includes unconstrained…

Optimization and Control · Mathematics 2021-07-20 Tianyi Lin , Zhengyuan Zhou , Panayotis Mertikopoulos , Michael I. Jordan

Neural Ordinary Differential Equations (Neural ODEs) represent continuous-time dynamics with neural networks, offering advancements for modeling and control tasks. However, training Neural ODEs requires solving differential equations at…

Machine Learning · Computer Science 2025-02-24 Mariia Shapovalova , Calvin Tsay

We present and mathematically analyze an online adjoint algorithm for the optimization of partial differential equations (PDEs). Traditional adjoint algorithms would typically solve a new adjoint PDE at each optimization iteration, which…

Optimization and Control · Mathematics 2022-01-27 Justin Sirignano , Konstantinos Spiliopoulos

The choice of how to retain information about past gradients dramatically affects the convergence properties of state-of-the-art stochastic optimization methods, such as Heavy-ball, Nesterov's momentum, RMSprop and Adam. Building on this…

Machine Learning · Computer Science 2020-03-13 Antonio Orvieto , Jonas Kohler , Aurelien Lucchi

In this work, we analyze two of the most fundamental algorithms in geodesically convex optimization: Riemannian gradient descent and (possibly inexact) Riemannian proximal point. We quantify their rates of convergence and produce different…

Optimization and Control · Mathematics 2024-03-18 David Martínez-Rubio , Christophe Roux , Sebastian Pokutta

Nonconvex-concave min-max problem arises in many machine learning applications including minimizing a pointwise maximum of a set of nonconvex functions and robust adversarial training of neural networks. A popular approach to solve this…

Optimization and Control · Mathematics 2025-03-21 Jiawei Zhang , Peijun Xiao , Ruoyu Sun , Zhi-Quan Luo

Motivated by the fact that the gradient-based optimization algorithms can be studied from the perspective of limiting ordinary differential equations (ODEs), here we derive an ODE representation of the accelerated triple momentum (TM)…

Optimization and Control · Mathematics 2020-08-26 Boya Sun , Jemin George , Solmaz Kia

A key appeal of the recently proposed Neural Ordinary Differential Equation (ODE) framework is that it seems to provide a continuous-time extension of discrete residual neural networks. As we show herein, though, trained Neural ODE models…

Machine Learning · Computer Science 2023-09-12 Katharina Ott , Prateek Katiyar , Philipp Hennig , Michael Tiemann

A commonly used heuristic in non-convex optimization is Normalized Gradient Descent (NGD) - a variant of gradient descent in which only the direction of the gradient is taken into account and its magnitude ignored. We analyze this heuristic…

Machine Learning · Computer Science 2016-11-22 Kfir Y. Levy

We analyze stochastic gradient descent for optimizing non-convex functions. In many cases for non-convex functions the goal is to find a reasonable local minimum, and the main concern is that gradient updates are trapped in saddle points.…

Machine Learning · Computer Science 2015-03-10 Rong Ge , Furong Huang , Chi Jin , Yang Yuan

A major approach to saddle point optimization $\min_x\max_y f(x, y)$ is a gradient based approach as is popularized by generative adversarial networks (GANs). In contrast, we analyze an alternative approach relying only on an oracle that…

Optimization and Control · Mathematics 2021-04-02 Youhei Akimoto

Escaping saddle points is a central research topic in nonconvex optimization. In this paper, we propose a simple gradient-based algorithm such that for a smooth function $f\colon\mathbb{R}^n\to\mathbb{R}$, it outputs an…

Optimization and Control · Mathematics 2021-11-30 Chenyi Zhang , Tongyang Li