Convergence rate of moments in stochastic approximation with simultaneous perturbation gradient approximation and resetting

László Gerencsér

52 citations0/0 files storedIEEE Transactions on Automatic Control

No readable copy stored yet — this record is metadata only.

No open-access location is known for this record yet.

Literature note Cite in a project Citation map

Simulation Techniques and Applications Reinforcement Learning in Robotics Adaptive Dynamic Programming Control

Abstract

The sequence of recursive estimators for function minimization generated by Spall's (1998) simultaneous perturbation stochastic approximation (SPSA) method, combined with a suitable restarting mechanism is considered. It is proved that this sequence converges under certain conditions with rate O(n/sup -/spl beta//2/) for some /spl beta/>0, the best value being /spl beta/=2/3, where the rate is measured by the L/sub q/-norm of the estimation error for any 1/spl les/q

Paper brief

Loading…

Cite this work

Citation unavailable for this work.

BibTeX RIS CSL-JSON

No public copy is stored for this record, so only the metadata is cited.

Citations in this library

Citation map →

Stored only when both papers are in the corpus — 52 citations exist upstream.

References

1992Multivariate stochastic approximation using a simultaneous perturbation gradient approximation 1978Stochastic Approximation Methods for Constrained and Unconstrained Systems 1980Controlled Diffusion Processes 1998Stochastic Approximation Algorithms and Applications 1968On Asymptotic Normality in Stochastic Approximation 1967Stochastic Approximation of Minima with Improved Asymptotic Speed

Cited by

1999Optimization over discrete sets via SPSA 2003Accelerated randomized stochastic optimization 1999Stochastic optimization and the simultaneous perturbation method 2014An Overview of Stochastic Approximation 2002Adaptive stochastic approximation by the simultaneous perturbation method 2016Adaptive System Optimization Using Random Directions Stochastic Approximation

Explore the map →

Papers that cite the same references — the relational fallback while embeddings are still backfilling.

Imported from OpenAlex (CC0) — nothing here is generated.