What cost function should used for logistic regression? 1 pointMean Squared Error Cross Entropy

The cost function that should be used for logistic regression is Cross Entropy.

Here's why:

1. Logistic regression is a classification algorithm, used when the output or target variable is a categorical or discrete value (like 0/1, Yes/No).

2. The goal of logistic regression is to find the best parameters that will predict the probability of an event occurring as accurately as possible.

3. The Cross Entropy cost function is suitable for this because it measures the performance of a classification model whose output is a probability value between 0 and 1.

4. Cross entropy increases as the predicted probability diverges from the actual label. So predicting a probability of .012 when the actual observation label is 1 would be bad and result in a high loss value. A perfect model would have a log loss of 0.

5. Mean Squared Error (MSE) is more suitable for regression problems where we have continuous output or target variable. Using MSE for logistic regression can lead to non-convexity with multiple local optima. It is not a good idea to use MSE for logistic regression.

So, for logistic regression, we should use the Cross Entropy cost function.