Effects of the Stochastic and Deterministic Movements in the Optimization Processes

Abstract

In this study, a linear function representing the iris data set is obtained by making use of the MLR model. SGD, Momentum, Adagrad, RMSProp, Adadelta and Adam optimization algorithms are used to find the optimum values of coefficients of this function. An initialization method with initial population is recommended for these coefficients, which are generally initialized with a fixed or random value in MLRs. IAE, ITAE, MSE and ISE error functions are used as objective functions in the MLR model used. Initial populations of the methods are developed by using a proposed deterministic and classical stochastic initialization methods between upper and lower bounds. The method that are initialized stochasticaly is run several times as seen in literature and the mean values are calculated. On the other hand, the application that is initialized deterministic is only run once. According to the results of deterministic and stochastic initialization methods, it is observed that the coefficients and iteration numbers obtained in both applications are close to each other. Despite very high temporal gain is achieved from the application that is initialized deterministic. As a result of the comparisons, the linear model obtained with Adadelta and MSE reaches the result in the shortest time.