English
Related papers

Related papers: Dimer-Enhanced Optimization: A First-Order Approac…

200 papers

We propose derivative-informed neural operators (DINOs), a general family of neural networks to approximate operators as infinite-dimensional mappings from input function spaces to output function spaces or quantities of interest. After…

Numerical Analysis · Mathematics 2023-10-18 Thomas O'Leary-Roseberry , Peng Chen , Umberto Villa , Omar Ghattas

With rapid advancements in machine learning, first-order algorithms have emerged as the backbone of modern optimization techniques, owing to their computational efficiency and low memory requirements. Recently, the connection between…

Quantum Physics · Physics 2025-05-21 Jiaqi Leng , Bin Shi

Deep learning methods based on backward stochastic differential equations (BSDEs) have emerged as competitive alternatives to physics-informed neural networks (PINNs) for solving high-dimensional partial differential equations (PDEs). By…

Machine Learning · Computer Science 2026-05-15 Jaemin Seo , Surin Lee , Jae Yong Lee

Real-world systems are often formulated as constrained optimization problems. Techniques to incorporate constraints into Neural Networks (NN), such as Neural Ordinary Differential Equations (Neural ODEs), have been used. However, these…

Machine Learning · Computer Science 2025-03-27 C. Coelho , M. Fernanda P. Costa , L. L. Ferrás

While first-order methods are popular for solving optimization problems that arise in large-scale deep learning problems, they come with some acute deficiencies. To diminish such shortcomings, there has been recent interest in applying…

Machine Learning · Computer Science 2023-10-05 Mahsa Yousefi , Angeles Martinez

Embedding nonlinear dynamical systems into artificial neural networks is a powerful new formalism for machine learning. By parameterizing ordinary differential equations (ODEs) as neural network layers, these Neural ODEs are…

Machine Learning · Computer Science 2024-10-28 Mikko Lehtimäki , Lassi Paunonen , Marja-Leena Linne

We propose a scalable preconditioned primal-dual hybrid gradient algorithm for solving partial differential equations (PDEs). We multiply the PDE with a dual test function to obtain an inf-sup problem whose loss functional involves…

Numerical Analysis · Mathematics 2026-05-26 Shu Liu , Stanley Osher , Wuchen Li

In modern decentralized applications, ensuring communication efficiency and privacy for the users are the key challenges. In order to train machine-learning models, the algorithm has to communicate to the data center and sample data for its…

Optimization and Control · Mathematics 2024-04-04 Hoang Huy Nguyen , Yan Li , Tuo Zhao

Large language models (LLMs) excel across various tasks, but standard first-order (FO) fine-tuning demands considerable memory, significantly limiting real-world deployment. Recently, zeroth-order (ZO) optimization stood out as a promising…

Machine Learning · Computer Science 2025-11-04 Qitao Tan , Jun Liu , Zheng Zhan , Caiwei Ding , Yanzhi Wang , Xiaolong Ma , Jaewoo Lee , Jin Lu , Geng Yuan

In stochastic gradient descent, especially for neural network training, there are currently dominating first order methods: not modeling local distance to minimum. This information required for optimal step size is provided by second order…

Machine Learning · Computer Science 2019-12-10 Jarek Duda

Despite their popularity in the field of continuous optimisation, second-order quasi-Newton methods are challenging to apply in machine learning, as the Hessian matrix is intractably large. This computational burden is exacerbated by the…

Machine Learning · Computer Science 2024-02-28 Elre T. Oldewage , Ross M. Clarke , José Miguel Hernández-Lobato

It is well known that finding a global optimum is extremely challenging for nonconvex optimization. There are some recent efforts \cite{anandkumar2016efficient, cartis2018second, cartis2020sharp, chen2019high} regarding the optimization…

Optimization and Control · Mathematics 2020-08-11 Xihua Zhu , Jiangze Han , Bo Jiang

Following the seminal work of Nesterov, accelerated optimization methods have been used to powerfully boost the performance of first-order, gradient-based parameter estimation in scenarios where second-order optimization strategies are…

Numerical Analysis · Computer Science 2017-11-28 Anthony Yezzi , Ganesh Sundaramoorthi

First-order algorithms have been popular for solving convex and non-convex optimization problems. A key assumption for the majority of these algorithms is that the gradient of the objective function is globally Lipschitz continuous, but…

Optimization and Control · Mathematics 2024-02-07 Junyu Zhang , Mingyi Hong

We introduce Hindsight-Guided Momentum (HGM), a first-order optimization algorithm that adaptively scales learning rates based on the directional consistency of recent updates. Traditional adaptive methods, such as Adam or RMSprop , adapt…

Optimization and Control · Mathematics 2025-07-01 Krisanu Sarkar

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

When training neural networks with custom objectives, such as ranking losses and shortest-path losses, a common problem is that they are, per se, non-differentiable. A popular approach is to continuously relax the objectives to provide…

Machine Learning · Computer Science 2024-10-28 Felix Petersen , Christian Borgelt , Tobias Sutter , Hilde Kuehne , Oliver Deussen , Stefano Ermon

A neural stochastic differential equation (SDE) is an SDE with drift and diffusion terms parametrized by neural networks. The training procedure for neural SDEs consists of optimizing the SDE vector field (neural network) parameters to…

Machine Learning · Computer Science 2025-11-04 Luke Snow , Vikram Krishnamurthy

Stochastic gradient descent and other first-order variants, such as Adam and AdaGrad, are commonly used in the field of deep learning due to their computational efficiency and low-storage memory requirements. However, these methods do not…

Optimization and Control · Mathematics 2025-02-19 Aditya Ranganath , Mukesh Singhal , Roummel Marcia

We introduce new optimized first-order methods for smooth unconstrained convex minimization. Drori and Teboulle recently described a numerical method for computing the $N$-iteration optimal step coefficients in a class of first-order…

Optimization and Control · Mathematics 2019-06-14 Donghwan Kim , Jeffrey A. Fessler