English
Related papers

Related papers: A Differential Equation for Modeling Nesterov's Ac…

200 papers

We consider a gradient approximation scheme that is based on applying needle shaped inputs. By using ideas known from the classic proof of the Pontryagin Maximum Principle we derive an approximation that reveals that the considered system…

Systems and Control · Computer Science 2016-03-15 Simon Michalowsky , Christian Ebenbauer

Optimization plays a key role in machine learning. Recently, stochastic second-order methods have attracted much attention due to their low computational cost in each iteration. However, these algorithms might perform poorly especially if…

Machine Learning · Computer Science 2017-10-25 Haishan Ye , Zhihua Zhang

We give a development of the ODE method for the analysis of recursive algorithms described by a stochastic recursion. With variability modelled via an underlying Markov process, and under general assumptions, the following results are…

Probability · Mathematics 2007-05-23 J. Huang , I. Kontoyiannis , S. P. Meyn

We propose an adaptive smoothing algorithm based on Nesterov's smoothing technique in \cite{Nesterov2005c} for solving "fully" nonsmooth composite convex optimization problems. Our method combines both Nesterov's accelerated proximal…

Optimization and Control · Mathematics 2016-07-05 Quoc Tran-Dinh

For minimizing a strongly convex objective function subject to linear inequality constraints, we consider a penalty approach that allows one to utilize stochastic methods for problems with a large number of constraints and/or objective…

Optimization and Control · Mathematics 2022-02-16 Meng Li , Paul Grigas , Alper Atamturk

Neural differential equations are a promising new member in the neural network family. They show the potential of differential equations for time series data analysis. In this paper, the strength of the ordinary differential equation (ODE)…

Machine Learning · Computer Science 2020-05-21 Mansura Habiba , Barak A. Pearlmutter

We develop two new variants of alternating direction methods of multipliers (ADMM) and two parallel primal-dual decomposition algorithms to solve a wide range class of constrained convex optimization problems. Our approach relies on a novel…

Optimization and Control · Mathematics 2018-06-15 Quoc Tran-Dinh , Yuzixuan Zhu

The continuous-time model of Nesterov's momentum provides a thought-provoking perspective for understanding the nature of the acceleration phenomenon in convex optimization. One of the main ideas in this line of research comes from the…

Optimization and Control · Mathematics 2021-07-13 Peiyuan Zhang , Antonio Orvieto , Hadi Daneshmand

In this paper we propose new numerical algorithms in the setting of unconstrained optimization problems and we study the rate of convergence in the iterates of the objective function. Furthermore, our algorithms are based upon splitting and…

Optimization and Control · Mathematics 2020-02-11 Cristian Daniel Alecsa

Two-step predictor/corrector methods are provided to solve three classes of problems that present themselves as systems of ordinary differential equations (ODEs). In the first class, velocities are given from which displacements are to be…

Numerical Analysis · Computer Science 2017-07-10 Alan D. Freed

We solve the local equivalence problem for second order (smooth or analytic) ordinary differential equations. We do so by presenting a {\em complete convergent normal form} for this class of ODEs. The normal form is optimal in the sense…

Dynamical Systems · Mathematics 2020-08-26 Ilya Kossovskiy , Dmitri Zaitsev

Recent works on optical flow estimation use neural networks to predict the flow field that maps positions of one image to positions of the other. These networks consist of a feature extractor, a correlation volume, and finally several…

Computer Vision and Pattern Recognition · Computer Science 2025-06-05 Leyla Mirvakhabova , Hong Cai , Jisoo Jeong , Hanno Ackermann , Farhad Zanjani , Fatih Porikli

We propose a simple interpolation-based method for the efficient approximation of gradients in neural ODE models. We compare it with the reverse dynamic method (known in the literature as "adjoint method") to train neural ODEs on…

Neural and Evolutionary Computing · Computer Science 2020-11-03 Talgat Daulbaev , Alexandr Katrutsa , Larisa Markeeva , Julia Gusak , Andrzej Cichocki , Ivan Oseledets

Motivated by an inertial primal-dual dynamical system with vanishing damping, we propose a class of accelerated augmented Lagrangian methods with Nesterov extrapolation parameters for a linearly constrained convex optimization problem with…

Optimization and Control · Mathematics 2026-05-28 Xin He , Nan-Jing Huang , Yi-Bin Xiao , Ya-Ping Fang

We present a distributed proximal-gradient method for optimizing the average of convex functions, each of which is the private local objective of an agent in a network with time-varying topology. The local objectives have distinct…

Distributed, Parallel, and Cluster Computing · Computer Science 2012-10-09 Annie I. Chen , Asuman Ozdaglar

We propose ADOM - an accelerated method for smooth and strongly convex decentralized optimization over time-varying networks. ADOM uses a dual oracle, i.e., we assume access to the gradient of the Fenchel conjugate of the individual loss…

Optimization and Control · Mathematics 2021-02-19 Dmitry Kovalev , Egor Shulgin , Peter Richtárik , Alexander Rogozin , Alexander Gasnikov

The solution of systems of non-autonomous linear ordinary differential equations is crucial in a variety of applications, such us nuclear magnetic resonance spectroscopy. A new method with spectral accuracy has been recently introduced in…

Numerical Analysis · Mathematics 2022-10-14 Stefano Pozza , Niel Van Buggenhout

We propose a machine learning framework to accelerate numerical computations of time-dependent ODEs and PDEs. Our method is based on recasting (generalizations of) existing numerical methods as artificial neural networks, with a set of…

Numerical Analysis · Mathematics 2019-03-08 Siddhartha Mishra

Nesterov's accelerated gradient descent (NAG) is one of the milestones in the history of first-order algorithms. It was not successfully uncovered until the high-resolution differential equation framework was proposed in [Shi et al., 2022]…

Optimization and Control · Mathematics 2022-12-13 Shuo Chen , Bin Shi , Ya-xiang Yuan

The graduated optimization approach, also known as the continuation method, is a popular heuristic to solving non-convex problems that has received renewed interest over the last decade. Despite its popularity, very little is known in terms…

Machine Learning · Computer Science 2015-07-28 Elad Hazan , Kfir Y. Levy , Shai Shalev-Shwartz