Convergence Analysis of Parametric Optimization Methods
This chapter deals with some simple convergence results related to the parametric optimization methods discussed in Chapter 7. The main idea underlying “convergence analysis” of a method is to identify (mathematically) the solution to which the method converges. Hence to prove that an algorithm works, one must show that the algorithm converges to the optimal solution. In this chapter, this is precisely what we will attempt to do with some algorithms of Chapter 7.
KeywordsMarkov Chain Simulated Annealing Stationary Point Gradient Descent Convergence Analysis
Unable to display preview. Download preview PDF.