Stochastic differential equations for modeling first order optimization methods
From MaRDI portal
Recommendations
- Stochastic modified equations and dynamics of stochastic gradient algorithms. I: Mathematical foundations
- Backward error analysis and the qualitative behaviour of stochastic optimization algorithms: application to stochastic coordinate descent
- Analysis of stochastic gradient descent in continuous time
- Stochastic heavy ball
- scientific article; zbMATH DE number 2052583
Cites work
- A differential equation for modeling Nesterov's accelerated gradient method: theory and insights
- An introduction to computational stochastic PDEs
- Characterizations of Łojasiewicz inequalities: Subgradient flows, talweg, convexity
- Convergence of the forward-backward algorithm: beyond the worst-case with the help of geometry
- Convergence rates of an inertial gradient descent algorithm under growth and flatness conditions
- Convergence rates of damped inertial dynamics under geometric conditions and perturbations
- Fast convergence of inertial dynamics and algorithms with asymptotic vanishing viscosity
- From error bounds to the complexity of first-order descent methods for convex functions
- scientific article; zbMATH DE number 3850830 (Why is no real title available?)
- scientific article; zbMATH DE number 3371284 (Why is no real title available?)
- Inertial forward-backward algorithms with perturbations: application to Tikhonov regularization
- On an inequality of Gronwall
- On semi- and subanalytic geometry
- On the convergence of gradient-like flows with noisy gradient input
- On the long time behavior of second order differential equations with asymptotically small dissipation
- Optimal convergence rates for Nesterov acceleration
- Optimization methods for large-scale machine learning
- Proximal Alternating Minimization and Projection Methods for Nonconvex Problems: An Approach Based on the Kurdyka-Łojasiewicz Inequality
- Some methods of speeding up the convergence of iteration methods
- Stochastic differential equations. An introduction with applications.
- The Łojasiewicz Inequality for Nonsmooth Subanalytic Functions with Applications to Subgradient Dynamical Systems
- Understanding the acceleration phenomenon via high-resolution differential equations
Cited in
(3)- Continuous‐time stochastic gradient descent for optimizing over the stationary distribution of stochastic differential equations
- Backward error analysis and the qualitative behaviour of stochastic optimization algorithms: application to stochastic coordinate descent
- Stochastic dual dynamical systems for linear equality constrained convex optimization problems
This page was built for publication: Stochastic differential equations for modeling first order optimization methods
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6490316)
