paper-with-me

Papers

Revisiting the Role of Euler Numerical Integration on Acceleration and Stability in Convex Optimization

2021-02-23 · Peiyuan Zhang, Antonio Orvieto, Hadi Daneshmand, Thomas Hofmann, Roy Smith

Viewing optimization methods as numerical integrators for ordinary differential equations (ODEs) provides a thought-provoking modern framework for studying accelerated first-order optimizers. In this literature, acceleration is often supposed to be linked to the quality of the integrator (accuracy, energy preservation, symplecticity). In this work, we propose a novel ordinary differential equation that questions this connection: both the explicit and the semi-implicit (a.k.a symplectic) Euler discretizations on this ODE lead to an accelerated algorithm for convex programming. Although semi-implicit methods are well-known in numerical analysis to enjoy many desirable features for the integration of physical systems, our findings show that these properties do not necessarily relate to acceleration.

📄 PDF Abstract BibTeX arXiv:2102.11537

Code (0)

등록된 구현이 없습니다.

Tasks

Numerical Integration

Similar Papers 제목 키워드 기반

Sharpen Your Flow: Sharpness-Aware Sampling for Flow Matching

2026-05-12 · Aditi Gupta, Soon Hoe Lim, Annan Yu, N. Benjamin Erichson arxiv

Flow matching models generate samples by numerically integrating a learned velocity field, with each integration step requiring a neural network evaluation. Fast generation therefore requires using a small fixed evaluati…

On the Role of Strain and Vorticity in Numerical Integration Error for Flow Matching

2026-04-22 · Chenxi Tao, Seung-Kyum Choi arxiv

Flow matching generates data by integrating a learned velocity field, where the number of integration steps (NFE) directly determines inference cost. We analyze which properties of the velocity field govern integration e…

A Dynamical Systems Perspective on Nesterov Acceleration

2019-05-17 · Michael Muehlebach, Michael. I. Jordan

We present a dynamical system framework for understanding Nesterov's accelerated gradient method. In contrast to earlier work, our derivation does not rely on a vanishing step size argument. We show that Nesterov acceler…

Continuous and Discrete-time Accelerated Stochastic Mirror Descent for Strongly Convex Functions

2018-07-01 · ICML 2018 7 · Pan Xu, Tianhao Wang, Quanquan Gu

We provide a second-order stochastic differential equation (SDE), which characterizes the continuous-time dynamics of accelerated stochastic mirror descent (ASMD) for strongly convex functions. This SDE plays a cent…

Stochastic Optimization

A Contraction Theory Approach to Optimization Algorithms from Acceleration Flows

2021-05-18 · Pedro Cisneros-Velarde, Francesco Bullo

Much recent interest has focused on the design of optimization algorithms from the discretization of an associated optimization flow, i.e., a system of differential equations (ODEs) whose trajectories solve an associated…