Optimization with momentum: dynamical, control-theoretic, and symplectic perspectives
From MaRDI portal
Publication:4998976
Authors: Michael Muehlebach, Michael Jordan 
Publication date: 9 July 2021
Full work available at URL: https://arxiv.org/abs/2002.12493
Recommendations
- Generalized momentum-based methods: a Hamiltonian perspective
- Conformal symplectic and relativistic optimization
- A Lyapunov analysis of accelerated methods in optimization
- The rate of convergence of optimization algorithms obtained via discretizations of heavy ball dynamical systems for convex optimization problems
- On dissipative symplectic integration with applications to gradient-based optimization
nonconvex optimizationsymplectic integrationgradient-based optimizationconvergence rate analysisNesterov acceleration
Cites Work
- Title not available (Why is that?)
- Introductory lectures on convex optimization. A basic course.
- Title not available (Why is that?)
- Analysis and design of optimization algorithms via integral quadratic constraints
- Nonlinear systems. Analysis, stability, and control
- Morse Theory. (AM-51)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- A differential equation for modeling Nesterov's accelerated gradient method: theory and insights
- Some methods of speeding up the convergence of iteration methods
- Title not available (Why is that?)
- Cubic regularization of Newton method and its global performance
- A trust region algorithm with a worst-case iteration complexity of \(\mathcal{O}(\epsilon ^{-3/2})\) for nonconvex optimization
- Fast convergence of inertial dynamics and algorithms with asymptotic vanishing viscosity
- A variational perspective on accelerated methods in optimization
- Stochastic heavy ball
- The approximate duality gap technique: a unified theory of first-order methods
- Asymptotic analysis of differential equations
Cited In (8)
- Optimization with Momentum: Dynamical, Control-Theoretic, and Symplectic Perspectives
- Fast optimization via inertial dynamics with closed-loop damping
- Title not available (Why is that?)
- Self-consistent dynamical field theory of kernel evolution in wide neural networks
- A control-theoretic perspective on optimal high-order optimization
- Decentralized concurrent learning with coordinated momentum and restart
- Accelerated optimization landscape of linear-quadratic regulator
- DYNAMICAL, SYMPLECTIC AND STOCHASTIC PERSPECTIVES ON GRADIENT-BASED OPTIMIZATION
This page was built for publication: Optimization with momentum: dynamical, control-theoretic, and symplectic perspectives
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4998976)
