Accelerated Performance and Accelerated Learning with Discrete-Time High-Order Tuners

2022/03/30 by Cui, Yingnan, Annaswamy, Anuradha M.
#Dynamical Systems (math.DS) #FOS: Mathematics #Optimization and Control (math.OC)

paper · doi:10.48550/arxiv.2203.16438

Abstract

We consider two high-order tuners that have been shown to have accelerated performance, one based on Polyak's heavy ball method and another based on Nesterov's acceleration method. We show that parameter estimates are bounded and converge to the true values exponentially fast when the regressors are persistently exciting. Simulation results corroborate the accelerated performance and accelerated learning properties of these high-order tuners in comparison to algorithms based on normalized gradient descent.

Related

• A High-order Tuner for Accelerated Learning and Control
• Discrete-Time High Order Tuner With A Time-Varying Learning Rate
• Concurrent learning in high-order tuners for parameter identification
• A Tuner that Accelerates Parameters
• Accelerated Learning with Robustness to Adversarial Regressors