Concentration bounds for stochastic approximations
From MaRDI portal
(Redirected from Publication:456280)
Abstract: We obtain non asymptotic concentration bounds for two kinds of stochastic approximations. We first consider the deviations between the expectation of a given function of the Euler scheme of some diffusion process at a fixed deterministic time and its empirical mean obtained by the Monte-Carlo procedure. We then give some estimates concerning the deviation between the value at a given time-step of a stochastic approximation algorithm and its target. Under suitable assumptions both concentration bounds turn out to be Gaussian. The key tool consists in exploiting accurately the concentration properties of the increments of the schemes. For the first case, as opposed to the previous work of Lemaire and Menozzi (EJP, 2010), we do not have any systematic bias in our estimates. Also, no specific non-degeneracy conditions are assumed.
Recommendations
- On some non asymptotic bounds for the Euler scheme
- Transport-entropy inequalities and deviation estimates for stochastic approximation schemes
- A concentration bound for contractive stochastic approximation
- Stochastic Approximation and Large Deviations: Upper Bounds and <scp>w.p.1</scp> Convergence
- A concentration bound for stochastic approximation via Alekseev's formula
Cited in
(24)- Asymptotic behavior of constrained stochastic approximations via the theory of large deviations
- Sharp non-asymptotic concentration inequalities for the approximation of the invariant distribution of a diffusion
- Concentration bounds for temporal difference learning with linear function approximation: the case of batch data and uniform sampling
- Non-asymptotic Gaussian estimates for the recursive approximation of the invariant distribution of a diffusion
- A concentration bound for contractive stochastic approximation
- A constructive proof of a concentration bound for real-valued random variables
- Conditional quantile sequential estimation for stochastic codes
- An improved probability bound for the approximate S-lemma
- Non-asymptotic error bounds for the multilevel Monte Carlo Euler method applied to SDEs with constant diffusion coefficient
- Corrigendum to: ``A concentration bound for contractive stochastic approximation
- Unifying presampling via concentration bounds
- Multi-level stochastic approximation algorithms
- Transport-entropy inequalities and deviation estimates for stochastic approximation schemes
- Recursive estimation in a class of models of deformation
- On the Lock-in Probability of Stochastic Approximation
- scientific article; zbMATH DE number 4113792 (Why is no real title available?)
- A multi-step Richardson-Romberg extrapolation method for stochastic approximation
- A concentration bound for stochastic approximation via Alekseev's formula
- Approximation of the invariant distribution for a class of ergodic jump diffusions
- Concentration of Contractive Stochastic Approximation and Reinforcement Learning
- Optimal bounds in normal approximation for many interacting worlds
- On some non asymptotic bounds for the Euler scheme
- Stochastic approximation and reinforcement learning: the interface and a little beyond
- A multilevel stochastic approximation algorithm for value-at-risk and expected shortfall estimation
This page was built for publication: Concentration bounds for stochastic approximations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q456280)
