Rate of convergence analysis of discrete simultaneous perturbation stochastic approximation algorithm

Wang, Qi; Spall, James C.

doi:10.1109/acc.2013.6580576

Cited by 9 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The D‐SPSA optimiser proposed by Wang et al. [38] calculates the objective function only at the integer positions. The optimiser needs only two measurements of the loss function at each iteration.…”

Section: Methodsmentioning

confidence: 99%

High‐resolution optical‐to‐SAR image registration using mutual information and SPSA optimisation

Paul¹,

Pati

2020

IET Image Processing

View full text Add to dashboard Cite

The high‐resolution optical and synthetic aperture radar (SAR) images are widely used in many remote sensing application areas such as image fusion and change detection where image registration is a fundamental step. The latest high‐resolution optical and SAR satellites and airborne systems provide geometrically corrected images which do not contain global deformations. Though the images do not have global differences, still, registration differences exist between these optical and SAR images. These registration differences should be minimised through an automatic registration method before using the images for the aforementioned applications. However, an automatic optical‐to‐SAR image registration is a challenging task due to the presence of significant nonlinear intensity differences as well as local geometric distortions between the images. In order to solve these problems, an automatic optical‐to‐SAR image registration method is proposed which can effectively handle the registration differences between the globally corrected high‐resolution images. In the proposed method, initially, a coarse registration is performed by using a discrete simultaneous perturbation stochastic approximation (SPSA) optimisation. Then, a smooth continuous SPSA optimisation is utilised for the fine registration of the images. Experiments are performed on six sets of high‐resolution optical‐SAR image pairs and the results show the effectiveness of the proposed method.

show abstract

Section: Methodsmentioning

confidence: 99%

High‐resolution optical‐to‐SAR image registration using mutual information and SPSA optimisation

Paul¹,

Pati

2020

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…In this chapter, we discuss the rate of convergence property of DSPSA. We have shown partial and preliminary results of this chapter in Wang and Spall (2013). We set up an upper bound for the finite sample performance and calculate the asymptotic performance of DSPSA in the big-O sense.…”

Section: Rate Of Convergencementioning

confidence: 99%

Discrete simultaneous perturbation stochastic approximation on loss function with noisy measurements

Wang

Spall

2011

Proceedings of the 2011 American Control Conference

Self Cite

View full text Add to dashboard Cite

Consider the stochastic optimization of a loss function defined on p-dimensional grid of points in Euclidean space. We introduce the middle point discrete simultaneous perturbation stochastic approximation (DSPSA) algorithm for such discrete problems and show that convergence to the minimum is achieved. Consistent with other stochastic approximation methods, this method formally accommodates noisy measurements of the loss function.

show abstract

“…Tuning the controller online by estimating the gradient of the goal function is an effective idea of the data-driven control. For instance, simultaneous perturbation stochastic approximation (SPSA) introduced by Spall estimates the gradient by stochastic approximation [4,5] and model free adaptive control (MFAC) proposed by Hou replaces the gradient with pseudo-partial derivative [6][7][8]. The idea of iterations also has good applications in data-driven method.…”

Section: Introductionmentioning

confidence: 99%

Data-driven controller design for general MIMO nonlinear systems via virtual reference feedback tuning and neural networks

et al. 2016

View full text Add to dashboard Cite

Rate of convergence analysis of discrete simultaneous perturbation stochastic approximation algorithm

Cited by 9 publications

References 11 publications

High‐resolution optical‐to‐SAR image registration using mutual information and SPSA optimisation

High‐resolution optical‐to‐SAR image registration using mutual information and SPSA optimisation

Discrete simultaneous perturbation stochastic approximation on loss function with noisy measurements

Data-driven controller design for general MIMO nonlinear systems via virtual reference feedback tuning and neural networks

Contact Info

Product

Resources

About