Overview#

Variance error is the amount that the estimate of the Mapping function will change if different Training dataset was used.

The Mapping function is estimated from the Training dataset by some machine learning algorithm, so we should expect the algorithm to have some variance. Ideally, it should not change too much from one Training dataset to the next, meaning that the algorithm is good at picking out the hidden underlying mapping between the inputs and the output variables.

Machine Learning algorithms that have a high [{$pagename}] are strongly in uenced by the specifics of the Training dataset. This means that the specifics of the training have in uences the number and types of parameters used to characterize the mapping function. ˆ

• Low Variance error - Suggests small changes to the estimate of the Mapping function with changes to the Training dataset ˆ
• High Variance error - Suggests large changes to the estimate of the Mapping function with changes to the Training dataset (Referred to a Overfitting)

Examples of low-Variance error Machine Learning algorithms include:

• Linear Regression
• Linear Discriminant Analysis
• Logistic Regression

Examples of high-Variance error Machine Learning algorithms include:

• Decision Trees
• k-Nearest Neighbors
• Support Vector Machines.

More Information#

There might be more information for this subject on one of the following:

• Machine Learning model
• Overfitting
• Underfitting