Research map / Optimization / Nonconvex and smooth optimization
ADMM and Accelerated ADMM as Continuous Dynamical Systems
Guilherme Franca, Daniel Robinson, Rene Vidal
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Derive continuous limit of ADMM as first-order ADMM flow (A^T A) X' + grad V(X) = 0 | ADMM · Synthetic quadratic (Figure 1) | agreement of trajectories with discrete ADMM | No clear effect |
| Use ADMM flow stability via Lyapunov function V(X)-V(X*) under strict local minimizer and isolated stationary point | ADMM flow · Theoretical stability | asymptotic stability | Improved |
| Use symplectic Euler integrator for A-ADMM flow to match discrete A-ADMM dynamics | A-ADMM flow · Synthetic quadratic (Figure 1) | agreement with discrete A-ADMM | No clear effect |
Closest papers by meaning
- Differential Inclusions for Modeling Nonsmooth ADMM Variants: A Continuous Limit Theory (ICML 2019 · similarity 0.91)
- A Lyapunov Analysis of Accelerated Methods in Optimization (JMLR 2021 · similarity 0.88)
- Trajectory of Alternating Direction Method of Multipliers and Adaptive Acceleration (NeurIPS 2019 · similarity 0.88)
- Fast ADMM Algorithm for Distributed Optimization with Adaptive Penalty (AAAI 2016 · similarity 0.86)
- Accelerated Variance Reduced Stochastic ADMM (AAAI 2017 · similarity 0.86)
- ADMM for Nonconvex Optimization under Minimal Continuity Assumption (ICLR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
