This project focuses on implementing optimization techniques for curve fitting and logistic regression. The objective is to find the best-fitting curves or parameters by minimizing the residuals or maximizing the log likelihood function.
[
]
The project involves applying optimization techniques to solve three different problems:
Simple Least Squares: The problem aims to find the best-fitting curve to a given set of points by minimizing the sum of the squares (residuals) of the points from the curve. The implementation utilizes optimization techniques to minimize the residuals and obtain the optimal curve.
Polynomial Curve Fitting: When the data follows a non-linear relationship, higher degree polynomial curves are used to fit the data points. Two methods are employed: optimizing the L2 norm and optimizing the L-infinity norm. The L2 norm measures the square root of the sum of squared vector values, while the L-infinity norm measures the maximum distance.
Logistic Regression: Logistic regression is a binary classification problem used to predict the outcome of independent variables (yes or no) based on the logistic function. In this project, the optimization technique involves maximizing the log likelihood function to obtain the optimal parameters for logistic regression.
