Quasi-stochastic approximation: Design principles with applications to extremum seeking control

CK Lauand, S Meyn - IEEE Control Systems Magazine, 2023‏ - ieeexplore.ieee.org
How can you optimize a function based on evaluations of this function without access to its
gradient? Kiefer and Wolfowitz proposed a solution in the early 1950s based on stochastic …

Approaching quartic convergence rates for quasi-stochastic approximation with application to gradient-free optimization

C Kalil Lauand, S Meyn - Advances in Neural Information …, 2022‏ - proceedings.neurips.cc
Stochastic approximation is a foundation for many algorithms found in machine learning and
optimization. It is in general slow to converge: the mean square error vanishes as $ O (n …

Markovian Foundations for Quasi-Stochastic Approximation

CK Lauand, S Meyn - SIAM Journal on Control and Optimization, 2025‏ - SIAM
This paper concerns quasi-stochastic approximation (QSA) to solve root finding problems
commonly found in applications to optimization and reinforcement learning. Theory is …

Markovian foundations for quasi-stochastic approximation with applications to extremum seeking control

CK Lauand, S Meyn - arxiv preprint arxiv:2207.06371, 2022‏ - arxiv.org
This paper concerns quasi-stochastic approximation (QSA) to solve root finding problems
commonly found in applications to optimization and reinforcement learning. The general …

Extremely fast convergence rates for extremum seeking control with Polyak-Ruppert averaging

CK Lauand, S Meyn - arxiv preprint arxiv:2206.00814, 2022‏ - arxiv.org
Stochastic approximation is a foundation for many algorithms found in machine learning and
optimization. It is in general slow to converge: the mean square error vanishes as $ O (n …