English
Related papers

Related papers: ODE-based Learning to Optimize

200 papers

Hessian-free (HF) optimization has been shown to effectively train deep autoencoders (Martens, 2010). In this paper, we aim to accelerate HF training of autoencoders by reducing the amount of data used in training. HF utilizes the conjugate…

Machine Learning · Computer Science 2025-04-21 Ibrahim Emirahmetoglu , David E. Stewart

A framework is introduced for sequentially solving convex stochastic minimization problems, where the objective functions change slowly, in the sense that the distance between successive minimizers is bounded. The minimization problems are…

Optimization and Control · Mathematics 2018-03-12 Craig Wilson , Venugopal Veeravalli , Angelia Nedich

We consider a class of convex optimization problems over the simplex of probability measures. Our framework comprises optimal experimental design (OED) problems, in which the measure over the design space indicates which experiments are…

Numerical Analysis · Mathematics 2020-04-20 Roland Herzog , Eric Legler

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,…

It has been observed that residual networks can be viewed as the explicit Euler discretization of an Ordinary Differential Equation (ODE). This observation motivated the introduction of so-called Neural ODEs, which allow more general…

Machine Learning · Computer Science 2021-04-21 Tianjun Zhang , Zhewei Yao , Amir Gholami , Kurt Keutzer , Joseph Gonzalez , George Biros , Michael Mahoney

This paper studies second-order methods for convex-concave minimax optimization. Monteiro and Svaiter (2012) proposed a method to solve the problem with an optimal iteration complexity of $\mathcal{O}(\epsilon^{-3/2})$ to find an…

Optimization and Control · Mathematics 2025-04-16 Lesi Chen , Chengchang Liu , Jingzhao Zhang

Learning to Optimize (L2O) is a subfield of machine learning (ML) in which ML models are trained to solve parametric optimization problems. The general goal is to learn a fast approximator of solutions to constrained optimization problems,…

Optimization and Control · Mathematics 2025-12-04 James Kotary , Himanshu Sharma , Ethan King , Draguna Vrabie , Ferdinando Fioretto , Jan Drgona

Recent developments in applying machine learning to address Alternating Current Optimal Power Flow (AC OPF) problems have demonstrated significant potential in providing close to optimal solutions for generator dispatch in near real-time.…

Systems and Control · Electrical Eng. & Systems 2024-10-28 Vincenzo Di Vito , Mostafa Mohammadian , Kyri Baker , Ferdinando Fioretto

We derive a second-order ordinary differential equation (ODE) which is the limit of Nesterov's accelerated gradient method. This ODE exhibits approximate equivalence to Nesterov's scheme and thus can serve as a tool for analysis. We show…

Machine Learning · Statistics 2015-10-29 Weijie Su , Stephen Boyd , Emmanuel J. Candes

Residual neural networks can be viewed as the forward Euler discretization of an Ordinary Differential Equation (ODE) with a unit time step. This has recently motivated researchers to explore other discretization approaches and train ODE…

Machine Learning · Computer Science 2019-07-02 Amir Gholami , Kurt Keutzer , George Biros

Learning neural ODEs often requires solving very stiff ODE systems, primarily using explicit adaptive step size ODE solvers. These solvers are computationally expensive, requiring the use of tiny step sizes for numerical stability and…

Applications abound in which optimization problems must be repeatedly solved, each time with new (but similar) data. Analytic optimization algorithms can be hand-designed to provably solve these problems in an iterative fashion. On one…

Optimization and Control · Mathematics 2022-09-28 Howard Heaton , Xiaohan Chen , Zhangyang Wang , Wotao Yin

We study a class of misspecified saddle point (SP) problems, where the optimization objective depends on an unknown parameter that must be learned concurrently from data. Unlike existing studies that assume parameters are fully known or…

Machine Learning · Computer Science 2025-10-08 Mohammad Mahdi Ahmadi , Erfan Yazdandoost Hamedani

This paper develops and analyzes an optimal-order semi-discrete scheme and its fully discrete finite element approximation for nonlinear stochastic elastic wave equations with multiplicative noise. A non-standard time-stepping scheme is…

Numerical Analysis · Mathematics 2025-04-08 Xiaobing Feng , Yukun Li , Liet Vo

The deployment of learning-based models in safety-critical control systems demands mathematical guarantees that standard regression architectures cannot provide. This paper presents an integrated framework that bridges Neural Ordinary…

Systems and Control · Electrical Eng. & Systems 2026-05-26 Lin Feng , Xin He

Mixtures of linear dynamical systems (MoLDS) provide a path to model time-series data that exhibit diverse temporal dynamics across trajectories. However, its application remains challenging in complex and noisy settings, limiting its…

Machine Learning · Computer Science 2026-03-02 Lulu Gong , Shreya Saxena

We study optimization algorithms for the finite sum problems frequently arising in machine learning applications. First, we propose novel variants of stochastic gradient descent with a variance reduction property that enables linear…

Machine Learning · Computer Science 2017-07-06 Jakub Konečný

Implicit layer deep learning techniques, like Neural Differential Equations, have become an important modeling framework due to their ability to adapt to new problems automatically. Training a neural differential equation is effectively a…

Machine Learning · Computer Science 2023-06-05 Avik Pal , Alan Edelman , Chris Rackauckas

The performance of deep (reinforcement) learning systems crucially depends on the choice of hyperparameters. Their tuning is notoriously expensive, typically requiring an iterative training process to run for numerous steps to convergence.…

Machine Learning · Computer Science 2021-01-19 Vu Nguyen , Sebastian Schulze , Michael A Osborne

Some continuous optimization methods can be connected to ordinary differential equations (ODEs) by taking continuous limits, and their convergence rates can be explained by the ODEs. However, since such ODEs can achieve any convergence rate…

Numerical Analysis · Mathematics 2022-07-15 Kansei Ushiyama , Shun Sato , Takayasu Matsuo