Implement gradient descent with momentum. Explain the concept of momentum and

demonstrate how it helps in accelerating convergence. Compare the performance of

gradient descent with and without momentum using a dataset of your choice.

Rubric for Implementing Gradient Descent with Momentum

Criteria:

$$ Implementation of Momentum $(7$ Points$)$:

$$ Correctly initializes velocity parameters.

$$ Properly integrates momentum into the parameter updates.

$$ Provides a clear explanation of the momentum concept.

$$ Performance Comparison $(3$ Points$)$:

$$ Compares with standard gradient descent showing convergence speed.

$$ Discusses the benefits of using momentum in terms of convergence

acceleration