A convergence analysis of the perturbed compositional gradient flow: averaging principle and normal deviations
From MaRDI portal
Publication:1659690
DOI10.3934/dcds.2018216zbMath1397.34098arXiv1709.00515MaRDI QIDQ1659690
Publication date: 22 August 2018
Published in: Discrete and Continuous Dynamical Systems (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1709.00515
averaging principle; stochastic gradient descent; perturbed gradient flow; normal deviation; fast-slow dynamical systems; perturbed compositional gradient flow; stochastic composite gradient descent
90C30: Nonlinear programming
34C29: Averaging method for ordinary differential equations
34F05: Ordinary differential equations and systems with randomness
Related Items
Central limit type theorem and large deviation principle for multi-scale McKean-Vlasov SDEs, Functional law of large numbers and central limit theorem for slow-fast McKean-Vlasov equations, Averaging principle and normal deviations for multiscale stochastic systems
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Stochastic compositional gradient descent: algorithms for minimizing compositions of expected-value functions
- Normal deviations from the averaged motion for some reaction-diffusion equations with fast oscillating perturbation
- Central limit theorem for additive functionals of reversible Markov processes and applications to simple exclusions
- The exit problem for small random perturbations of dynamical systems with a hyperbolic fixed point
- On Poisson equation and diffusion approximation. II.
- On the diffusion approximation of nonconvex stochastic gradient descent
- On the Poisson equation and diffusion approximation. III
- On the Poisson equation and diffusion approximation. I
- Diffusion approximation for slow motion in fully coupled averaging
- A Khasminskii type averaging principle for stochastic reaction-diffusion equations
- Periodic homogenization for hypoelliptic diffusions
- On Polynomial Mixing and Convergence Rate for Stochastic Difference and Differential Equations
- Functional Integration and Partial Differential Equations. (AM-109)
- Asymptotics of superregular perturbations of fiber ergodic semigroups
- Accelerating Stochastic Composition Optimization
- On Stochastic Processes Defined by Differential Equations with a Small Parameter
- Stochastic differential equations. An introduction with applications.