Fast optimistic gradient descent ascent (OGDA) method in continuous and discrete time
From MaRDI portal
convergence of iteratesconvergence of trajectoriesconvergence ratesextragradient methodLyapunov analysismonotone equationNesterov's accelerated gradient methodoptimistic gradient descent ascent (OGDA) methodvariational inequality
Monotone operators and generalizations (47H05) Variational and other types of inequalities involving nonlinear operators (general) (47J20) Numerical optimization and variational techniques (65K10) Numerical methods for variational inequalities and related problems (65K15) Complexity and performance of numerical algorithms (65Y20) Nonlinear programming (90C30) Methods of reduced gradient type (90C52)
Cites work
- A continuous dynamical Newton-like approach to solving monotone inclusions
- A differential equation for modeling Nesterov's accelerated gradient method: theory and insights
- A forward-backward splitting method for monotone inclusions without cocoercivity
- A modification of the Arrow-Hurwicz method for search of saddle points
- Accelerated proximal point method for maximally monotone operators
- Benchmarking optimization software with performance profiles.
- Continuous Newton-like inertial dynamics for monotone inclusions
- Convergence of a relaxed inertial forward-backward algorithm for structured monotone inclusions
- Convergence of inertial dynamics and proximal algorithms governed by maximally monotone operators
- Convergence of iterates for first-order optimization algorithms with inertia and Hessian driven damping
- Convex analysis and monotone operator theory in Hilbert spaces
- Dual extrapolation and its applications to solving variational inequalities and related problems
- Dynamics of evolutionary equations
- Evolution equations for maximal monotone operators: asymptotic analysis in continuous and discrete time
- Fast convergence of dynamical ADMM via time scaling of damped inertial dynamics
- Fast convex optimization via inertial dynamics with Hessian driven damping
- Fast Proximal Methods via Time Scaling of Damped Inertial Dynamics
- First-order optimization algorithms via inertial systems with Hessian driven damping
- Fixed points of nonexpanding maps
- scientific article; zbMATH DE number 3850830 (Why is no real title available?)
- scientific article; zbMATH DE number 3498726 (Why is no real title available?)
- scientific article; zbMATH DE number 3534286 (Why is no real title available?)
- scientific article; zbMATH DE number 3575377 (Why is no real title available?)
- scientific article; zbMATH DE number 3376275 (Why is no real title available?)
- Improved convergence rates and trajectory convergence for primal-dual dynamical systems with vanishing damping
- Introductory lectures on convex optimization. A basic course.
- Lower complexity bounds of first-order methods for convex-concave bilinear saddle-point problems
- New Proximal Point Algorithms for Convex Minimization
- Newton-like dynamics and forward-backward methods for structured monotone inclusions in Hilbert spaces
- Newton-like inertial dynamics and proximal algorithms governed by maximally monotone operators
- On the Convergence of the Proximal Point Algorithm for Convex Minimization
- Shadow Douglas-Rachford splitting for monotone inclusions
- The rate of convergence of Nesterov's accelerated forward-backward method is actually faster than 1/k^2
- Two steps at a time-taking GAN training in stride with Tseng's method
- Understanding the acceleration phenomenon via high-resolution differential equations
- Weak convergence of the sequence of successive approximations for nonexpansive mappings
Cited in
(10)- Strong convergence and fast rates for dynamical systems with Tikhonov regularization
- Long-time analysis of stochastic heavy ball dynamics for convex optimization and monotone equations
- Symplectic discretization approach for developing new proximal point algorithm
- Accelerated forward-backward algorithms with subgradient corrections
- Fast reflected forward-backward algorithm: achieving fast convergence rates for convex optimization with linear cone constraints
- Accelerating preconditioned ADMM via degenerate proximal point mappings
- On a stochastic differential equation with correction term governed by a monotone and Lipschitz continuous operator
- Recovering Nesterov accelerated dynamics from heavy ball dynamics via time rescaling
- Tikhonov regularization of monotone operator flows not only ensures strong convergence of the trajectories but also speeds up the vanishing of the residuals
- Fast second-order dynamics with slow vanishing damping approaching the zeros of a monotone and continuous operator
This page was built for publication: Fast optimistic gradient descent ascent (OGDA) method in continuous and discrete time
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7025995)
