AN EXAMPLE OF IMPLEMENTING THE CLASSICAL AND STOCHASTIC GRADIENT DESCENT METHODS

The article considers the classical gradient descent method – a numerical method for finding the local minimum of a function by moving along an antigradient, and its modification – the stochastic gradient descent method, in which movement is performed along the antigradient of a part of the variables. The methods considered are implemented in the Python programming language and an example of their application is given for predicting the final mark of students based on the "Students Performance" dataset. The source data is taken from the Kaggle website.